[2026-03-25 15:35:37,337][mllm.models.large_language_model_local][INFO] - Initializing adapter 'agent_adapter': no initial weights provided or found; starting from scratch. [2026-03-25 15:35:38,072][mllm.models.adapter_training_wrapper][INFO] - Adapter 'agent_adapter': initialized with fresh weights (no initial weights found). [2026-03-25 15:35:38,078][mllm.models.large_language_model_local][INFO] - Initializing adapter 'critic_adapter': no initial weights provided or found; starting from scratch. [2026-03-25 15:35:38,774][mllm.models.adapter_training_wrapper][INFO] - Adapter 'critic_adapter': initialized with fresh weights (no initial weights found). [2026-03-25 15:39:25,271][__main__][INFO] - Starting iteration 0. [2026-03-25 15:39:25,274][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:39:25,275][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:39:39,774][__main__][INFO] - Number of regex retries in iteration 0: 0 [2026-03-25 15:39:39,775][__main__][INFO] - agents played in iteration 0 are Bob, Alice [2026-03-25 15:40:11,564][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:40:12,086][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:40:14,959][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:40:15,993][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:40:16,979][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:40:17,473][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:40:17,969][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:40:18,463][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:40:18,958][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:40:19,596][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:40:20,090][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:40:20,583][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:40:21,076][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:40:21,571][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:40:22,065][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:40:22,558][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:40:23,051][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:40:23,543][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:40:24,046][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:40:24,823][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:40:25,318][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:40:26,446][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:40:26,940][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:40:27,437][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:40:27,932][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:40:28,427][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:40:29,044][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:40:29,538][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:40:30,033][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:40:30,528][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:40:31,022][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:40:31,516][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:40:32,012][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:40:32,505][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:40:33,000][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:40:33,496][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:40:33,991][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:40:34,485][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:40:34,977][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:40:35,472][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:40:35,967][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:40:36,462][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:40:36,957][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:40:37,454][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:40:37,951][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:40:38,448][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:40:38,945][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:40:39,622][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:40:40,118][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:40:40,613][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:40:41,108][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:40:42,105][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:40:42,599][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:40:43,095][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:40:43,993][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:40:44,489][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 15:40:44,985][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 15:40:45,482][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 15:40:45,974][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 15:40:46,471][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 15:40:46,966][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 15:40:47,460][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 15:40:47,955][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 15:40:48,447][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 15:40:48,939][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 15:40:49,432][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 15:40:49,925][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 15:40:50,418][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 15:40:50,911][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 15:40:51,402][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 15:40:51,895][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 15:40:52,389][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 15:40:52,880][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 15:40:53,373][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 15:40:53,867][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 15:40:54,362][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 15:40:54,853][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 15:40:55,347][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 15:40:55,839][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 15:40:56,331][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 15:40:56,824][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 15:40:57,316][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 15:40:57,810][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 15:40:58,306][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 15:40:58,800][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 15:40:59,295][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 15:40:59,789][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 15:41:00,282][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 15:41:00,775][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 15:41:01,268][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 15:41:01,761][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 15:41:02,254][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 15:41:02,747][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 15:41:03,240][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 15:41:03,733][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 15:41:04,228][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 15:41:04,722][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 15:41:05,215][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 15:41:05,708][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 15:41:06,202][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 15:41:06,697][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 15:41:07,190][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 15:41:07,684][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 15:41:08,178][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 15:41:08,673][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 15:41:09,168][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 15:41:09,663][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 15:41:10,157][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 15:41:10,654][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 15:41:11,150][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 15:41:11,644][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 15:41:12,139][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 15:41:12,634][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 15:41:13,128][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 15:41:13,622][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 15:41:14,117][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 15:41:14,612][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 15:41:15,108][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 15:41:16,232][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 15:41:16,729][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 15:41:17,814][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 15:41:18,308][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 15:41:18,803][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 15:41:19,297][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 15:41:19,793][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 15:41:20,289][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 15:41:20,785][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 15:41:21,278][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 15:41:21,772][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 15:41:22,264][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19398 tokens. [2026-03-25 15:41:24,017][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 15.85%, Current % of VRAM taken: 53.30%, Block Peak % of device VRAM: 61.12%, ΔTime: 00:01:11 [2026-03-25 15:41:24,653][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 15:41:24,656][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 15:41:24,658][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 15:41:25,394][__main__][INFO] - Iteration 1 took 2m 0s (12.07% Gen, 87.32% Train). Generation: 14s, Training: 1m 44s. Estimated remaining time: 99h 59m 48s. Estimated total time: 100h 6m 0s. Time estimates for 10 more iterations: 20m 1s, 100 more iterations: 3h 20m 12s, 500 more iterations: 16h 41m 0s. [2026-03-25 15:41:25,396][__main__][INFO] - Starting iteration 1. [2026-03-25 15:41:26,535][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:41:26,536][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:41:28,373][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:41:34,670][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 0 books, 20 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:41:36,344][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:41:41,069][__main__][INFO] - Number of regex retries in iteration 1: 3 [2026-03-25 15:41:41,069][__main__][INFO] - agents played in iteration 1 are Bob, Alice [2026-03-25 15:41:43,004][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:41:44,056][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:41:45,683][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:41:46,812][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:41:47,306][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:41:47,800][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:41:48,429][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:41:48,923][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:41:49,417][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:41:49,911][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:41:51,007][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:41:51,501][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:41:51,995][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:41:52,490][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:41:52,982][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:41:53,476][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:41:54,535][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:41:55,029][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:41:55,522][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:41:56,020][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:41:56,514][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:41:57,008][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:41:57,502][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:41:57,997][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:41:58,492][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:41:58,988][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:41:59,481][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:41:59,975][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:42:00,469][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:42:00,962][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:42:01,455][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:42:01,948][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:42:02,441][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:42:02,934][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:42:03,428][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:42:03,922][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:42:04,415][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:42:04,912][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:42:05,406][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:42:05,900][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:42:06,396][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:42:06,890][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:42:07,385][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:42:07,878][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:42:08,373][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:42:08,869][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:42:09,363][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:42:09,857][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:42:10,351][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:42:10,845][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:42:11,339][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:42:11,834][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:42:12,328][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:42:12,821][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:42:13,314][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:42:13,807][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 15:42:14,301][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 15:42:14,794][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 15:42:15,289][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 15:42:15,784][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 15:42:16,278][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 15:42:16,772][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 15:42:17,267][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 15:42:17,761][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 15:42:18,253][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 15:42:18,747][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 15:42:19,240][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 15:42:19,734][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 15:42:20,227][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 15:42:20,720][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 15:42:21,213][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 15:42:21,710][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 15:42:22,204][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 15:42:22,698][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 15:42:23,193][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 15:42:23,690][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 15:42:24,183][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 15:42:24,678][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 15:42:25,170][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 15:42:25,665][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 15:42:26,159][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 15:42:26,654][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 15:42:27,147][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 15:42:27,640][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 15:42:28,134][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 15:42:28,627][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 15:42:29,119][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 15:42:29,613][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 15:42:30,105][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 15:42:30,599][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 15:42:31,092][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 15:42:31,585][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 15:42:32,077][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 15:42:32,569][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 15:42:33,062][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 15:42:33,555][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 15:42:34,049][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 15:42:34,539][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 15:42:35,033][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 15:42:35,529][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 15:42:36,022][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 15:42:36,516][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 15:42:37,009][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 15:42:37,503][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 15:42:37,997][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 15:42:38,491][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 15:42:38,984][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 15:42:39,477][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 15:42:39,972][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 15:42:40,469][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 15:42:40,963][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 15:42:41,457][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 15:42:41,952][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 15:42:42,446][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 15:42:42,939][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 15:42:43,433][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 15:42:43,927][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 15:42:44,421][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 15:42:44,915][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 15:42:45,409][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 15:42:45,902][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 15:42:46,396][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 15:42:46,891][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 15:42:47,385][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 15:42:47,879][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 15:42:48,540][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 15:42:49,352][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 15:42:49,849][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 15:42:50,341][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 15:42:51,003][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19346 tokens. [2026-03-25 15:42:52,000][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.01%, Current % of VRAM taken: 60.37%, Block Peak % of device VRAM: 61.59%, ΔTime: 00:01:07 [2026-03-25 15:42:52,703][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 15:42:52,705][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 15:42:52,707][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 15:42:53,444][__main__][INFO] - Iteration 2 took 1m 26s (16.72% Gen, 82.43% Train). Generation: 14s, Training: 1m 11s. Estimated remaining time: 72h 17m 54s. Estimated total time: 72h 25m 34s. Time estimates for 10 more iterations: 14m 29s, 100 more iterations: 2h 24m 51s, 500 more iterations: 12h 4m 15s. [2026-03-25 15:42:53,446][__main__][INFO] - Starting iteration 2. [2026-03-25 15:42:54,486][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:42:54,486][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:42:56,310][mllm.models.large_language_model_local][WARNING] - Response Proposal: 5 hats, 5 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:43:01,652][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:43:08,510][__main__][INFO] - Number of regex retries in iteration 2: 2 [2026-03-25 15:43:08,513][__main__][INFO] - agents played in iteration 2 are Bob, Alice [2026-03-25 15:43:10,960][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:43:12,022][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:43:13,642][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:43:15,393][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:43:16,398][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:43:16,894][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:43:17,389][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:43:17,884][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:43:18,964][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:43:19,459][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:43:19,954][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:43:20,447][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:43:20,942][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:43:21,436][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:43:21,932][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:43:22,428][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:43:23,236][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:43:23,733][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:43:24,228][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:43:24,721][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:43:25,214][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:43:25,710][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:43:26,205][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:43:26,697][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:43:27,192][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:43:27,685][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:43:28,180][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:43:28,673][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:43:29,168][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:43:29,663][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:43:30,156][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:43:30,651][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:43:31,145][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:43:31,637][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:43:32,130][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:43:32,621][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:43:33,114][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:43:33,607][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:43:34,102][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:43:34,595][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:43:35,089][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:43:35,582][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:43:36,075][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:43:36,569][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:43:37,062][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:43:37,557][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:43:38,050][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:43:38,543][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:43:39,037][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:43:39,531][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:43:40,026][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:43:40,520][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:43:41,644][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:43:42,141][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:43:42,636][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:43:43,132][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 15:43:44,267][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 15:43:45,127][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 15:43:45,623][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 15:43:46,117][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 15:43:46,613][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 15:43:47,108][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 15:43:47,603][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 15:43:48,481][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 15:43:48,976][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 15:43:49,472][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 15:43:49,965][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 15:43:50,459][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 15:43:50,956][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 15:43:51,451][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 15:43:51,944][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 15:43:52,439][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 15:43:52,935][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 15:43:53,431][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 15:43:53,926][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 15:43:54,420][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 15:43:54,915][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 15:43:55,409][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 15:43:55,905][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 15:43:56,400][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 15:43:56,896][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 15:43:57,391][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 15:43:57,885][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 15:43:58,378][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 15:43:58,873][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 15:43:59,367][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 15:43:59,859][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 15:44:00,352][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 15:44:00,849][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 15:44:01,342][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 15:44:01,836][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 15:44:02,330][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 15:44:02,826][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 15:44:03,320][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 15:44:03,814][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 15:44:04,309][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 15:44:04,803][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 15:44:05,297][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 15:44:05,791][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 15:44:06,284][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 15:44:06,777][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 15:44:07,271][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 15:44:07,764][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 15:44:08,255][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 15:44:08,749][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 15:44:09,242][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 15:44:09,735][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 15:44:10,230][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 15:44:10,723][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 15:44:11,217][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 15:44:11,711][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 15:44:12,205][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 15:44:12,700][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 15:44:13,195][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 15:44:13,690][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 15:44:14,184][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 15:44:14,681][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 15:44:15,177][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 15:44:15,673][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 15:44:16,168][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 15:44:17,214][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 15:44:17,710][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 15:44:18,205][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 15:44:18,700][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 15:44:19,195][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 15:44:19,691][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 15:44:20,187][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 15:44:20,683][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 15:44:21,178][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 15:44:21,672][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19163 tokens. [2026-03-25 15:44:23,448][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 13.98%, Current % of VRAM taken: 60.34%, Block Peak % of device VRAM: 61.62%, ΔTime: 00:01:11 [2026-03-25 15:44:24,153][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 15:44:24,157][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 15:44:24,159][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 15:44:24,842][__main__][INFO] - Iteration 3 took 1m 30s (15.52% Gen, 83.72% Train). Generation: 14s, Training: 1m 15s. Estimated remaining time: 75h 8m 37s. Estimated total time: 75h 17m 48s. Time estimates for 10 more iterations: 15m 3s, 100 more iterations: 2h 30m 35s, 500 more iterations: 12h 32m 58s. [2026-03-25 15:44:24,843][__main__][INFO] - Starting iteration 3. [2026-03-25 15:44:25,930][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:44:25,931][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:44:39,963][__main__][INFO] - Number of regex retries in iteration 3: 0 [2026-03-25 15:44:39,964][__main__][INFO] - agents played in iteration 3 are Bob, Alice [2026-03-25 15:44:42,413][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:44:43,478][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:44:45,097][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:44:46,843][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:44:47,337][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:44:47,830][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:44:48,718][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:44:49,212][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:44:49,707][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:44:50,201][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:44:51,329][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:44:52,196][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:44:52,691][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:44:53,187][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:44:53,680][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:44:54,175][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:44:54,670][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:44:55,164][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:44:55,658][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:44:56,155][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:44:56,650][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:44:57,144][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:44:57,638][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:44:58,133][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:44:58,626][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:44:59,121][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:44:59,617][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:45:00,114][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:45:00,610][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:45:01,109][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:45:01,606][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:45:02,100][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:45:02,596][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:45:03,092][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:45:03,589][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:45:04,085][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:45:04,580][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:45:05,074][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:45:05,569][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:45:06,065][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:45:07,015][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:45:07,834][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:45:08,329][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:45:08,824][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:45:09,319][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:45:09,814][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:45:10,309][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:45:11,225][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:45:11,721][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:45:12,216][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:45:12,710][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:45:13,204][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:45:13,698][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:45:14,193][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:45:14,689][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:45:15,184][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 15:45:15,678][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 15:45:16,174][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 15:45:16,671][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 15:45:17,168][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 15:45:17,663][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 15:45:18,158][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 15:45:19,065][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 15:45:19,560][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 15:45:20,055][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 15:45:20,551][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 15:45:21,045][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 15:45:21,540][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 15:45:22,034][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 15:45:22,529][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 15:45:23,024][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 15:45:23,517][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 15:45:24,012][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 15:45:24,506][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 15:45:25,001][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 15:45:25,498][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 15:45:25,995][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 15:45:26,491][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 15:45:26,986][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 15:45:27,480][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 15:45:27,976][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 15:45:28,471][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 15:45:28,966][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 15:45:29,461][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 15:45:29,955][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 15:45:30,450][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 15:45:30,944][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 15:45:31,439][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 15:45:31,934][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 15:45:32,430][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 15:45:32,927][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 15:45:33,423][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 15:45:33,918][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 15:45:34,416][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 15:45:34,912][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 15:45:35,406][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 15:45:35,902][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 15:45:36,397][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 15:45:36,894][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 15:45:37,391][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 15:45:37,888][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 15:45:38,383][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 15:45:38,878][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 15:45:39,372][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 15:45:39,868][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 15:45:40,363][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 15:45:40,857][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 15:45:41,353][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 15:45:41,848][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 15:45:42,343][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 15:45:42,838][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 15:45:43,334][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 15:45:43,830][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 15:45:44,328][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 15:45:44,821][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 15:45:45,316][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 15:45:45,810][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 15:45:46,303][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 15:45:46,797][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 15:45:47,292][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 15:45:47,787][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 15:45:48,280][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 15:45:48,776][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 15:45:49,271][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 15:45:49,767][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 15:45:50,261][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 15:45:50,756][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 15:45:51,251][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 15:45:51,748][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 15:45:52,243][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19283 tokens. [2026-03-25 15:45:54,046][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 13.99%, Current % of VRAM taken: 60.35%, Block Peak % of device VRAM: 61.56%, ΔTime: 00:01:10 [2026-03-25 15:45:54,754][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 15:45:54,756][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 15:45:54,757][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 15:45:56,237][__main__][INFO] - Iteration 4 took 1m 30s (15.54% Gen, 82.82% Train). Generation: 14s, Training: 1m 14s. Estimated remaining time: 75h 4m 38s. Estimated total time: 75h 15m 21s. Time estimates for 10 more iterations: 15m 3s, 100 more iterations: 2h 30m 30s, 500 more iterations: 12h 32m 33s. [2026-03-25 15:45:56,239][__main__][INFO] - Starting iteration 4. [2026-03-25 15:45:57,395][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:45:57,395][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:46:11,162][__main__][INFO] - Number of regex retries in iteration 4: 0 [2026-03-25 15:46:11,163][__main__][INFO] - agents played in iteration 4 are Bob, Alice [2026-03-25 15:46:13,010][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:46:14,072][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:46:15,692][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:46:16,819][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:46:17,313][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:46:18,306][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:46:18,799][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:46:19,331][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:46:19,826][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:46:20,322][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:46:20,818][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:46:21,314][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:46:21,808][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:46:22,303][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:46:22,796][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:46:23,290][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:46:23,783][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:46:24,278][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:46:24,774][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:46:25,270][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:46:25,764][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:46:26,259][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:46:26,756][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:46:27,253][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:46:27,747][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:46:28,241][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:46:28,736][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:46:29,232][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:46:29,725][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:46:30,219][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:46:30,714][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:46:31,209][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:46:31,704][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:46:32,200][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:46:32,694][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:46:33,189][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:46:33,681][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:46:34,175][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:46:34,671][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:46:35,165][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:46:35,659][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:46:36,153][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:46:36,647][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:46:37,140][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:46:37,634][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:46:38,128][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:46:38,622][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:46:39,116][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:46:39,609][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:46:40,105][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:46:40,600][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:46:41,093][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:46:41,587][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:46:42,081][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:46:42,574][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:46:43,067][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 15:46:43,559][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 15:46:44,053][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 15:46:44,546][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 15:46:45,041][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 15:46:45,536][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 15:46:46,032][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 15:46:46,525][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 15:46:47,018][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 15:46:47,513][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 15:46:48,009][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 15:46:48,503][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 15:46:48,999][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 15:46:49,494][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 15:46:49,989][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 15:46:50,483][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 15:46:50,978][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 15:46:51,474][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 15:46:51,969][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 15:46:52,463][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 15:46:52,956][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 15:46:53,450][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 15:46:53,944][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 15:46:54,437][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 15:46:54,931][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 15:46:55,423][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 15:46:55,917][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 15:46:56,412][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 15:46:56,907][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 15:46:57,402][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 15:46:57,899][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 15:46:58,395][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 15:46:58,890][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 15:46:59,383][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 15:46:59,878][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 15:47:00,373][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 15:47:00,868][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 15:47:01,361][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 15:47:01,854][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 15:47:02,347][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 15:47:02,842][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 15:47:03,336][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 15:47:03,831][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 15:47:04,325][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 15:47:04,818][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 15:47:05,310][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 15:47:05,805][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 15:47:06,301][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 15:47:06,795][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 15:47:07,289][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 15:47:07,782][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 15:47:08,275][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 15:47:08,771][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 15:47:09,265][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 15:47:09,757][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 15:47:10,250][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 15:47:10,742][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 15:47:11,236][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 15:47:11,731][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 15:47:12,224][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 15:47:12,716][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 15:47:13,210][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 15:47:13,704][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 15:47:14,197][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 15:47:14,692][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 15:47:15,185][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 15:47:15,680][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 15:47:16,175][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 15:47:16,668][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 15:47:17,164][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 15:47:17,659][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 15:47:18,153][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 15:47:18,647][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 15:47:19,141][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 15:47:19,635][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19204 tokens. [2026-03-25 15:47:21,155][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 13.99%, Current % of VRAM taken: 60.35%, Block Peak % of device VRAM: 61.54%, ΔTime: 00:01:07 [2026-03-25 15:47:21,858][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 15:47:21,862][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 15:47:21,863][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 15:47:22,532][__main__][INFO] - Iteration 5 took 1m 25s (16.17% Gen, 83.04% Train). Generation: 13s, Training: 1m 10s. Estimated remaining time: 70h 44m 50s. Estimated total time: 70h 56m 59s. Time estimates for 10 more iterations: 14m 11s, 100 more iterations: 2h 21m 53s, 500 more iterations: 11h 49m 29s. [2026-03-25 15:47:22,534][__main__][INFO] - Starting iteration 5. [2026-03-25 15:47:23,629][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:47:23,629][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:47:25,524][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:47:25,526][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:47:27,645][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:47:37,038][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 20 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:47:38,093][__main__][INFO] - Number of regex retries in iteration 5: 4 [2026-03-25 15:47:38,094][__main__][INFO] - agents played in iteration 5 are Bob, Alice [2026-03-25 15:47:40,167][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:47:41,223][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:47:42,844][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:47:43,972][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:47:44,468][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:47:44,963][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:47:45,460][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:47:45,954][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:47:46,449][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:47:47,196][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:47:47,692][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:47:48,187][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:47:49,077][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:47:49,953][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:47:50,450][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:47:50,948][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:47:51,444][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:47:51,940][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:47:52,589][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:47:53,431][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:47:54,171][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:47:55,173][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:47:55,668][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:47:56,173][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:47:56,670][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:47:57,165][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:47:57,659][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:47:58,153][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:47:58,649][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:47:59,144][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:47:59,639][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:48:00,134][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:48:00,629][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:48:01,125][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:48:02,017][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:48:02,512][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:48:03,006][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:48:03,501][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:48:03,996][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:48:04,491][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:48:04,985][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:48:05,479][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:48:05,974][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:48:06,469][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:48:07,240][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:48:07,737][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:48:08,233][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:48:08,730][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:48:09,226][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:48:09,723][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:48:10,218][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:48:10,712][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:48:11,206][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:48:11,700][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:48:12,195][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:48:12,690][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 15:48:13,184][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 15:48:13,676][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 15:48:14,172][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 15:48:14,668][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 15:48:15,161][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 15:48:15,656][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 15:48:16,150][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 15:48:16,644][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 15:48:17,140][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 15:48:17,635][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 15:48:18,129][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 15:48:18,624][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 15:48:19,119][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 15:48:19,615][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 15:48:20,111][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 15:48:20,604][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 15:48:21,099][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 15:48:21,594][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 15:48:22,091][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 15:48:22,586][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 15:48:23,081][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 15:48:23,577][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 15:48:24,072][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 15:48:24,568][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 15:48:25,064][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 15:48:25,559][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 15:48:26,056][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 15:48:26,551][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 15:48:27,047][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 15:48:27,544][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 15:48:28,039][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 15:48:28,535][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 15:48:29,033][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 15:48:29,530][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 15:48:30,025][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 15:48:30,520][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 15:48:31,016][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 15:48:31,510][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 15:48:32,004][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 15:48:32,498][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 15:48:32,994][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 15:48:33,491][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 15:48:33,986][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 15:48:34,481][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 15:48:34,976][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 15:48:35,472][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 15:48:35,969][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 15:48:36,465][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 15:48:36,959][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 15:48:37,454][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 15:48:37,949][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 15:48:38,445][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 15:48:38,941][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 15:48:39,436][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 15:48:39,931][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 15:48:40,427][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 15:48:40,921][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 15:48:41,419][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 15:48:41,915][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 15:48:42,410][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 15:48:42,903][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 15:48:43,396][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 15:48:43,891][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 15:48:44,384][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 15:48:44,878][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 15:48:45,372][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 15:48:45,867][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 15:48:46,361][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 15:48:46,860][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 15:48:47,355][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 15:48:47,852][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 15:48:48,345][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 15:48:48,840][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 15:48:49,335][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19357 tokens. [2026-03-25 15:48:50,924][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 13.99%, Current % of VRAM taken: 60.35%, Block Peak % of device VRAM: 61.62%, ΔTime: 00:01:09 [2026-03-25 15:48:51,640][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 15:48:51,643][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 15:48:51,644][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 15:48:52,355][__main__][INFO] - Iteration 6 took 1m 28s (16.30% Gen, 82.89% Train). Generation: 14s, Training: 1m 13s. Estimated remaining time: 73h 42m 47s. Estimated total time: 73h 56m 26s. Time estimates for 10 more iterations: 14m 47s, 100 more iterations: 2h 27m 52s, 500 more iterations: 12h 19m 24s. [2026-03-25 15:48:52,357][__main__][INFO] - Starting iteration 6. [2026-03-25 15:48:53,407][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:48:53,408][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:49:07,443][__main__][INFO] - Number of regex retries in iteration 6: 0 [2026-03-25 15:49:07,444][__main__][INFO] - agents played in iteration 6 are Bob, Alice [2026-03-25 15:49:09,890][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:49:10,948][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:49:12,575][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:49:14,323][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:49:15,328][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:49:16,190][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:49:16,686][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:49:17,183][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:49:17,940][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:49:18,436][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:49:18,931][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:49:19,427][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:49:19,922][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:49:20,419][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:49:20,915][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:49:21,409][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:49:21,905][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:49:22,401][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:49:22,897][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:49:23,394][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:49:23,890][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:49:24,387][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:49:24,881][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:49:25,379][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:49:25,874][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:49:26,369][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:49:26,865][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:49:27,362][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:49:27,859][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:49:28,355][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:49:28,850][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:49:29,347][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:49:29,842][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:49:30,338][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:49:30,835][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:49:31,331][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:49:31,825][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:49:32,319][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:49:32,815][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:49:33,310][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:49:33,806][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:49:34,303][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:49:34,798][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:49:35,293][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:49:35,790][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:49:36,286][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:49:36,780][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:49:37,275][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:49:37,770][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:49:38,265][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:49:38,761][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:49:39,255][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:49:39,752][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:49:40,247][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:49:40,743][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:49:41,238][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 15:49:41,734][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 15:49:42,229][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 15:49:42,722][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 15:49:43,216][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 15:49:43,709][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 15:49:44,202][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 15:49:44,696][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 15:49:45,191][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 15:49:45,684][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 15:49:46,179][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 15:49:46,674][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 15:49:47,169][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 15:49:47,664][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 15:49:48,161][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 15:49:48,657][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 15:49:49,154][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 15:49:49,651][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 15:49:50,146][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 15:49:50,640][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 15:49:51,136][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 15:49:51,631][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 15:49:52,127][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 15:49:52,624][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 15:49:53,119][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 15:49:53,615][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 15:49:54,110][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 15:49:54,606][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 15:49:55,101][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 15:49:55,596][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 15:49:56,091][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 15:49:56,587][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 15:49:57,082][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 15:49:57,576][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 15:49:58,071][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 15:49:58,567][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 15:49:59,064][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 15:49:59,561][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 15:50:00,057][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 15:50:00,553][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 15:50:01,050][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 15:50:01,544][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 15:50:02,040][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 15:50:02,536][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 15:50:03,032][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 15:50:03,526][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 15:50:04,020][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 15:50:04,515][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 15:50:05,011][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 15:50:05,506][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 15:50:06,001][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 15:50:06,496][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 15:50:06,992][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 15:50:07,486][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 15:50:07,982][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 15:50:08,477][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 15:50:08,974][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 15:50:09,470][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 15:50:09,967][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 15:50:10,462][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 15:50:10,957][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 15:50:11,453][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 15:50:11,950][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 15:50:12,447][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 15:50:12,944][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 15:50:13,439][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 15:50:13,935][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 15:50:14,428][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 15:50:14,921][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 15:50:15,415][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 15:50:15,910][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 15:50:16,404][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 15:50:16,898][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 15:50:17,392][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 15:50:17,886][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19241 tokens. [2026-03-25 15:50:18,531][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 13.92%, Current % of VRAM taken: 60.28%, Block Peak % of device VRAM: 61.66%, ΔTime: 00:01:07 [2026-03-25 15:50:19,243][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 15:50:19,248][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 15:50:19,249][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 15:50:19,911][__main__][INFO] - Iteration 7 took 1m 26s (16.23% Gen, 83.00% Train). Generation: 14s, Training: 1m 11s. Estimated remaining time: 71h 50m 15s. Estimated total time: 72h 5m 21s. Time estimates for 10 more iterations: 14m 25s, 100 more iterations: 2h 24m 10s, 500 more iterations: 12h 0m 53s. [2026-03-25 15:50:19,913][__main__][INFO] - Starting iteration 7. [2026-03-25 15:50:20,319][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:50:20,319][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:50:32,575][__main__][INFO] - Number of regex retries in iteration 7: 0 [2026-03-25 15:50:32,575][__main__][INFO] - agents played in iteration 7 are Bob, Alice [2026-03-25 15:50:33,430][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:50:34,019][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:50:34,473][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:50:34,972][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:50:35,468][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:50:35,964][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:50:36,459][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:50:36,956][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:50:37,451][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:50:37,947][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:50:38,444][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:50:38,939][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:50:39,436][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:50:39,932][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:50:40,427][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:50:40,923][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:50:41,420][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:50:41,916][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:50:42,411][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:50:42,927][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:50:43,422][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:50:43,919][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:50:44,417][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:50:44,915][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:50:45,412][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:50:45,908][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:50:46,403][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:50:46,898][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:50:47,393][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:50:47,888][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:50:48,383][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:50:48,877][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:50:49,373][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:50:49,868][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:50:50,363][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:50:50,859][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:50:51,353][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:50:51,848][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:50:52,344][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:50:52,845][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:50:53,342][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:50:53,838][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:50:54,334][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:50:54,830][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:50:55,326][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:50:55,821][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:50:56,315][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:50:56,811][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:50:57,306][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:50:57,801][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:50:58,297][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:50:58,791][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:50:59,285][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:50:59,778][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:51:00,272][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:51:00,765][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 15:51:01,259][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 15:51:01,753][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 15:51:02,253][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 15:51:02,748][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 15:51:03,243][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 15:51:03,738][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 15:51:04,234][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 15:51:04,730][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 15:51:05,225][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 15:51:05,721][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 15:51:06,215][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 15:51:06,708][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 15:51:07,202][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 15:51:07,697][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 15:51:08,192][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 15:51:08,688][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 15:51:09,183][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 15:51:09,679][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 15:51:10,176][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 15:51:10,671][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 15:51:11,166][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 15:51:11,662][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 15:51:12,157][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 15:51:12,652][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 15:51:13,148][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 15:51:13,642][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 15:51:14,137][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 15:51:14,633][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 15:51:15,130][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 15:51:15,626][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 15:51:16,123][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 15:51:16,619][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 15:51:17,117][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 15:51:17,614][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 15:51:18,108][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 15:51:18,605][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 15:51:19,099][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 15:51:19,595][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 15:51:20,091][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 15:51:20,585][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 15:51:21,080][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 15:51:21,575][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 15:51:22,071][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 15:51:22,565][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 15:51:23,061][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 15:51:23,556][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 15:51:24,052][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 15:51:24,548][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 15:51:25,045][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 15:51:25,539][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 15:51:26,036][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 15:51:26,531][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 15:51:27,026][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 15:51:27,521][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 15:51:28,015][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 15:51:28,511][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 15:51:29,007][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 15:51:29,503][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 15:51:29,998][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 15:51:30,492][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 15:51:30,986][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 15:51:31,480][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 15:51:31,976][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 15:51:32,472][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 15:51:32,967][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 15:51:33,459][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 15:51:33,956][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 15:51:34,452][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 15:51:34,949][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 15:51:35,445][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 15:51:35,941][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 15:51:36,436][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 15:51:36,931][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 15:51:37,426][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19441 tokens. [2026-03-25 15:51:38,531][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 13.99%, Current % of VRAM taken: 60.35%, Block Peak % of device VRAM: 61.70%, ΔTime: 00:01:04 [2026-03-25 15:51:39,243][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 15:51:39,246][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 15:51:39,247][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 15:51:40,010][__main__][INFO] - Iteration 8 took 1m 19s (15.38% Gen, 83.66% Train). Generation: 12s, Training: 1m 6s. Estimated remaining time: 66h 8m 9s. Estimated total time: 66h 24m 36s. Time estimates for 10 more iterations: 13m 16s, 100 more iterations: 2h 12m 49s, 500 more iterations: 11h 4m 6s. [2026-03-25 15:51:40,012][__main__][INFO] - Starting iteration 8. [2026-03-25 15:51:41,051][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:51:41,052][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:51:55,197][__main__][INFO] - Number of regex retries in iteration 8: 0 [2026-03-25 15:51:55,197][__main__][INFO] - agents played in iteration 8 are Bob, Alice [2026-03-25 15:51:57,492][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:51:58,558][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:52:00,173][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:52:01,921][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:52:02,918][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:52:03,412][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:52:03,906][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:52:04,400][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:52:04,895][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:52:05,389][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:52:06,408][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:52:07,281][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:52:08,142][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:52:08,637][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:52:09,133][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:52:09,628][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:52:10,655][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:52:11,594][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:52:12,091][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:52:12,584][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:52:13,080][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:52:13,575][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:52:14,072][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:52:14,568][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:52:15,063][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:52:15,559][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:52:16,053][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:52:16,548][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:52:17,043][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:52:17,538][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:52:18,032][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:52:18,527][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:52:19,023][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:52:19,517][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:52:20,011][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:52:20,505][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:52:21,001][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:52:21,497][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:52:21,993][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:52:22,490][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:52:22,984][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:52:23,480][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:52:24,571][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:52:25,069][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:52:25,565][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:52:26,061][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:52:26,558][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:52:27,053][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:52:27,549][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:52:28,045][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:52:28,540][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:52:29,036][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:52:29,534][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:52:30,032][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:52:30,530][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:52:31,024][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 15:52:31,522][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 15:52:32,018][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 15:52:32,515][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 15:52:33,012][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 15:52:33,510][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 15:52:34,007][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 15:52:34,503][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 15:52:35,002][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 15:52:35,499][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 15:52:35,997][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 15:52:36,493][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 15:52:36,987][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 15:52:37,482][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 15:52:37,976][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 15:52:38,470][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 15:52:38,965][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 15:52:39,459][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 15:52:39,953][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 15:52:40,449][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 15:52:40,946][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 15:52:41,444][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 15:52:41,941][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 15:52:42,437][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 15:52:42,934][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 15:52:43,433][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 15:52:43,931][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 15:52:44,427][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 15:52:44,921][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 15:52:45,416][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 15:52:45,911][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 15:52:46,407][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 15:52:46,901][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 15:52:47,396][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 15:52:47,891][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 15:52:48,387][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 15:52:48,881][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 15:52:49,376][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 15:52:49,871][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 15:52:50,365][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 15:52:50,860][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 15:52:51,355][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 15:52:51,849][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 15:52:52,342][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 15:52:52,836][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 15:52:53,332][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 15:52:53,829][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 15:52:54,322][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 15:52:54,818][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 15:52:55,313][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 15:52:55,809][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 15:52:56,306][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 15:52:56,803][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 15:52:57,300][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 15:52:57,796][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 15:52:58,294][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 15:52:58,791][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 15:52:59,289][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 15:52:59,785][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 15:53:00,281][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 15:53:00,778][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 15:53:01,275][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 15:53:01,773][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 15:53:02,271][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 15:53:02,766][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 15:53:03,262][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 15:53:03,758][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 15:53:04,254][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 15:53:04,752][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 15:53:05,250][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 15:53:05,746][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 15:53:06,243][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 15:53:06,739][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 15:53:07,236][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 15:53:07,732][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19486 tokens. [2026-03-25 15:53:09,149][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.01%, Current % of VRAM taken: 60.37%, Block Peak % of device VRAM: 61.72%, ΔTime: 00:01:10 [2026-03-25 15:53:09,879][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 15:53:09,881][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 15:53:09,882][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 15:53:10,537][__main__][INFO] - Iteration 9 took 1m 29s (15.81% Gen, 83.46% Train). Generation: 14s, Training: 1m 14s. Estimated remaining time: 74h 16m 27s. Estimated total time: 74h 34m 24s. Time estimates for 10 more iterations: 14m 54s, 100 more iterations: 2h 29m 8s, 500 more iterations: 12h 25m 44s. [2026-03-25 15:53:10,539][__main__][INFO] - Starting iteration 9. [2026-03-25 15:53:11,629][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:53:11,630][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:53:13,502][mllm.models.large_language_model_local][WARNING] - Response Proposal: 5 hats, 0 books, 5 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:53:25,978][__main__][INFO] - Number of regex retries in iteration 9: 1 [2026-03-25 15:53:25,979][__main__][INFO] - agents played in iteration 9 are Bob, Alice [2026-03-25 15:53:28,113][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:53:29,179][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:53:30,800][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:53:31,921][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:53:32,419][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:53:32,916][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:53:33,544][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:53:34,040][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:53:34,537][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:53:35,033][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:53:35,528][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:53:36,165][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:53:36,659][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:53:37,156][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:53:37,652][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:53:38,146][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:53:38,641][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:53:39,136][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:53:39,634][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:53:40,131][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:53:40,626][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:53:41,122][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:53:41,619][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:53:42,114][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:53:42,609][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:53:43,104][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:53:44,009][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:53:44,872][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:53:45,370][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:53:46,481][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:53:47,386][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:53:48,325][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:53:48,822][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:53:49,320][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:53:49,818][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:53:50,313][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:53:50,809][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:53:51,307][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:53:51,802][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:53:52,297][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:53:52,793][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:53:53,288][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:53:53,784][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:53:54,279][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:53:54,775][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:53:55,272][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:53:55,768][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:53:56,265][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:53:56,761][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:53:57,256][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:53:57,752][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:53:58,247][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:53:58,741][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:53:59,236][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:53:59,730][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:54:00,225][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 15:54:00,719][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 15:54:01,213][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 15:54:01,709][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 15:54:02,205][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 15:54:02,701][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 15:54:03,197][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 15:54:03,694][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 15:54:04,192][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 15:54:04,689][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 15:54:05,184][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 15:54:05,680][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 15:54:06,175][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 15:54:06,674][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 15:54:07,170][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 15:54:07,668][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 15:54:08,164][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 15:54:08,660][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 15:54:09,155][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 15:54:09,651][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 15:54:10,150][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 15:54:10,645][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 15:54:11,140][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 15:54:11,636][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 15:54:12,132][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 15:54:12,629][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 15:54:13,149][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 15:54:13,646][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 15:54:14,143][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 15:54:14,638][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 15:54:15,135][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 15:54:15,630][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 15:54:16,126][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 15:54:16,620][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 15:54:17,116][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 15:54:17,613][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 15:54:18,112][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 15:54:18,609][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 15:54:19,106][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 15:54:19,603][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 15:54:20,100][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 15:54:20,597][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 15:54:21,335][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 15:54:21,831][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 15:54:22,327][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 15:54:22,823][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 15:54:23,319][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 15:54:23,816][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 15:54:24,311][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 15:54:24,805][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 15:54:25,299][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 15:54:25,796][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 15:54:26,293][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 15:54:26,791][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 15:54:27,286][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 15:54:27,783][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 15:54:28,280][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 15:54:28,777][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 15:54:29,273][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 15:54:29,767][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 15:54:30,263][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 15:54:30,757][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 15:54:31,252][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 15:54:31,745][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 15:54:32,238][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 15:54:32,733][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 15:54:33,230][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 15:54:33,725][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 15:54:34,221][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 15:54:34,717][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 15:54:35,215][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 15:54:35,713][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 15:54:36,210][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 15:54:36,705][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 15:54:37,201][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19406 tokens. [2026-03-25 15:54:38,914][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.00%, Current % of VRAM taken: 60.36%, Block Peak % of device VRAM: 61.68%, ΔTime: 00:01:09 [2026-03-25 15:54:39,546][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 15:54:39,549][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 15:54:39,550][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 15:54:40,148][__main__][INFO] - Iteration 10 took 1m 28s (16.21% Gen, 83.11% Train). Generation: 14s, Training: 1m 13s. Estimated remaining time: 73h 26m 39s. Estimated total time: 73h 46m 6s. Time estimates for 10 more iterations: 14m 45s, 100 more iterations: 2h 27m 32s, 500 more iterations: 12h 17m 41s. [2026-03-25 15:54:40,151][__main__][INFO] - Starting iteration 10. [2026-03-25 15:54:41,387][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:54:41,388][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:54:55,579][__main__][INFO] - Number of regex retries in iteration 10: 0 [2026-03-25 15:54:55,581][__main__][INFO] - agents played in iteration 10 are Bob, Alice [2026-03-25 15:54:57,872][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:54:58,938][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:55:00,552][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:55:02,306][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:55:03,303][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:55:03,799][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:55:04,919][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:55:05,415][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:55:05,913][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:55:06,411][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:55:06,910][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:55:07,406][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:55:07,903][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:55:08,400][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:55:08,895][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:55:09,393][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:55:10,280][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:55:10,778][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:55:11,274][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:55:11,770][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:55:12,267][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:55:12,762][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:55:13,258][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:55:13,755][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:55:14,253][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:55:14,750][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:55:15,246][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:55:15,743][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:55:16,239][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:55:16,735][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:55:17,232][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:55:17,729][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:55:18,224][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:55:18,721][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:55:19,218][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:55:19,716][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:55:20,740][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:55:21,558][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:55:22,055][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:55:22,552][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:55:23,047][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:55:23,543][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:55:24,039][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:55:24,534][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:55:25,031][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:55:25,528][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:55:26,024][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:55:26,521][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:55:27,017][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:55:27,514][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:55:28,009][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:55:28,504][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:55:28,999][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:55:29,495][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:55:29,992][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:55:30,488][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 15:55:30,985][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 15:55:31,481][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 15:55:31,977][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 15:55:32,473][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 15:55:32,968][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 15:55:33,462][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 15:55:33,957][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 15:55:34,452][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 15:55:34,947][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 15:55:35,442][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 15:55:35,937][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 15:55:36,435][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 15:55:36,933][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 15:55:37,430][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 15:55:37,927][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 15:55:38,423][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 15:55:38,919][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 15:55:39,415][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 15:55:39,911][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 15:55:40,406][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 15:55:40,901][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 15:55:41,398][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 15:55:41,894][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 15:55:42,393][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 15:55:43,390][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 15:55:43,888][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 15:55:44,384][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 15:55:44,880][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 15:55:45,377][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 15:55:45,874][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 15:55:46,372][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 15:55:46,870][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 15:55:47,367][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 15:55:47,865][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 15:55:48,363][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 15:55:48,860][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 15:55:49,357][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 15:55:49,854][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 15:55:50,351][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 15:55:50,846][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 15:55:51,343][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 15:55:51,840][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 15:55:52,337][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 15:55:52,835][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 15:55:53,333][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 15:55:53,831][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 15:55:54,328][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 15:55:54,825][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 15:55:55,320][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 15:55:55,818][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 15:55:56,314][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 15:55:56,811][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 15:55:57,306][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 15:55:57,803][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 15:55:58,299][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 15:55:58,796][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 15:55:59,292][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 15:55:59,789][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 15:56:00,284][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 15:56:00,779][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 15:56:01,275][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 15:56:01,771][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 15:56:02,265][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 15:56:02,760][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 15:56:03,256][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 15:56:03,752][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 15:56:04,248][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 15:56:04,744][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 15:56:05,239][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 15:56:05,734][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 15:56:06,230][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 15:56:06,725][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 15:56:07,220][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 15:56:07,716][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19415 tokens. [2026-03-25 15:56:09,519][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 13.96%, Current % of VRAM taken: 60.32%, Block Peak % of device VRAM: 61.68%, ΔTime: 00:01:10 [2026-03-25 15:56:10,252][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 15:56:10,254][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 15:56:10,256][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 15:56:10,864][__main__][INFO] - Iteration 11 took 1m 29s (15.86% Gen, 83.46% Train). Generation: 14s, Training: 1m 14s. Estimated remaining time: 74h 12m 58s. Estimated total time: 74h 33m 56s. Time estimates for 10 more iterations: 14m 54s, 100 more iterations: 2h 29m 7s, 500 more iterations: 12h 25m 39s. [2026-03-25 15:56:10,866][__main__][INFO] - Starting iteration 11. [2026-03-25 15:56:11,993][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:56:11,993][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:56:13,847][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:56:13,850][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:56:15,079][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:56:26,425][__main__][INFO] - Number of regex retries in iteration 11: 3 [2026-03-25 15:56:26,426][__main__][INFO] - agents played in iteration 11 are Bob, Alice [2026-03-25 15:56:28,482][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:56:29,547][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:56:31,166][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:56:32,290][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:56:32,785][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:56:33,882][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:56:34,379][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:56:34,875][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:56:35,372][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:56:35,869][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:56:36,365][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:56:36,859][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:56:37,357][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:56:37,853][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:56:38,351][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:56:38,846][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:56:39,342][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:56:39,837][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:56:40,896][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:56:41,759][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:56:42,641][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:56:43,138][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:56:43,635][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:56:44,134][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:56:44,632][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:56:45,129][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:56:45,626][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:56:46,122][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:56:46,619][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:56:47,117][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:56:47,615][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:56:48,112][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:56:48,608][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:56:49,105][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:56:49,601][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:56:50,099][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:56:50,595][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:56:51,092][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:56:51,587][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:56:52,082][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:56:52,578][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:56:53,074][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:56:53,570][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:56:54,064][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:56:54,559][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:56:55,054][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:56:55,550][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:56:56,044][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:56:56,539][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:56:57,034][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:56:57,530][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:56:58,027][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:56:58,523][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:56:59,018][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:56:59,516][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:57:00,014][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 15:57:00,512][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 15:57:01,010][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 15:57:01,507][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 15:57:02,006][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 15:57:02,672][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 15:57:03,171][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 15:57:03,666][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 15:57:04,163][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 15:57:04,661][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 15:57:05,157][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 15:57:05,653][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 15:57:06,149][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 15:57:06,646][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 15:57:07,142][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 15:57:07,637][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 15:57:08,134][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 15:57:08,631][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 15:57:09,128][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 15:57:09,623][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 15:57:10,117][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 15:57:10,613][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 15:57:11,110][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 15:57:11,607][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 15:57:12,102][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 15:57:12,598][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 15:57:13,094][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 15:57:13,591][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 15:57:14,088][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 15:57:14,585][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 15:57:15,081][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 15:57:15,577][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 15:57:16,073][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 15:57:16,569][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 15:57:17,066][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 15:57:17,562][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 15:57:18,057][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 15:57:18,554][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 15:57:19,052][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 15:57:19,548][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 15:57:20,044][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 15:57:20,539][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 15:57:21,036][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 15:57:21,532][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 15:57:22,029][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 15:57:22,525][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 15:57:23,019][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 15:57:23,514][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 15:57:24,008][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 15:57:24,503][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 15:57:24,998][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 15:57:25,493][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 15:57:25,986][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 15:57:26,480][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 15:57:26,974][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 15:57:27,470][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 15:57:27,963][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 15:57:28,458][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 15:57:28,952][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 15:57:29,699][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 15:57:30,543][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 15:57:31,040][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 15:57:31,535][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 15:57:32,032][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 15:57:32,530][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 15:57:33,155][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 15:57:33,651][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 15:57:34,146][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 15:57:34,644][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 15:57:35,645][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 15:57:36,140][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 15:57:36,636][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 15:57:37,134][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 15:57:37,632][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 15:57:38,129][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19422 tokens. [2026-03-25 15:57:39,264][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 13.99%, Current % of VRAM taken: 60.35%, Block Peak % of device VRAM: 61.70%, ΔTime: 00:01:09 [2026-03-25 15:57:39,986][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 15:57:39,989][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 15:57:39,990][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 15:57:40,627][__main__][INFO] - Iteration 12 took 1m 28s (16.28% Gen, 83.00% Train). Generation: 14s, Training: 1m 13s. Estimated remaining time: 73h 29m 18s. Estimated total time: 73h 51m 45s. Time estimates for 10 more iterations: 14m 46s, 100 more iterations: 2h 27m 43s, 500 more iterations: 12h 18m 37s. [2026-03-25 15:57:40,630][__main__][INFO] - Starting iteration 12. [2026-03-25 15:57:41,742][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:57:41,743][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:57:56,101][__main__][INFO] - Number of regex retries in iteration 12: 0 [2026-03-25 15:57:56,102][__main__][INFO] - agents played in iteration 12 are Bob, Alice [2026-03-25 15:57:58,231][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:57:59,300][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:58:00,913][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:58:02,661][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:58:03,155][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:58:03,666][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:58:04,162][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:58:04,656][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:58:05,151][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:58:05,647][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:58:06,280][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:58:06,775][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:58:07,272][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:58:08,040][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:58:08,890][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:58:09,385][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:58:09,880][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:58:10,592][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:58:11,502][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:58:11,999][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:58:13,114][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:58:13,611][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:58:14,106][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:58:14,604][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:58:15,099][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:58:15,595][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:58:16,093][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:58:16,599][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:58:17,099][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:58:17,596][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:58:18,093][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:58:18,591][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:58:19,088][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:58:19,585][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:58:20,081][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:58:20,577][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:58:21,072][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:58:21,570][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:58:22,065][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:58:22,561][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:58:23,056][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:58:23,551][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:58:24,572][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:58:25,070][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:58:25,568][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:58:26,067][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:58:26,564][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:58:27,061][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:58:27,559][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:58:28,057][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:58:28,554][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:58:29,049][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:58:29,544][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:58:30,041][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:58:30,538][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:58:31,035][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 15:58:31,532][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 15:58:32,029][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 15:58:32,526][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 15:58:33,023][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 15:58:33,519][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 15:58:34,015][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 15:58:34,512][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 15:58:35,017][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 15:58:35,517][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 15:58:36,015][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 15:58:36,518][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 15:58:37,014][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 15:58:37,510][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 15:58:38,006][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 15:58:38,502][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 15:58:38,998][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 15:58:39,494][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 15:58:39,991][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 15:58:40,488][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 15:58:40,986][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 15:58:41,482][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 15:58:41,979][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 15:58:42,475][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 15:58:42,973][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 15:58:43,469][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 15:58:43,964][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 15:58:44,462][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 15:58:44,959][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 15:58:45,459][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 15:58:45,958][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 15:58:46,456][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 15:58:46,954][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 15:58:47,451][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 15:58:47,946][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 15:58:48,443][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 15:58:48,943][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 15:58:49,440][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 15:58:49,939][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 15:58:50,436][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 15:58:50,935][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 15:58:51,431][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 15:58:51,928][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 15:58:52,423][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 15:58:52,918][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 15:58:53,412][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 15:58:53,909][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 15:58:54,405][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 15:58:54,900][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 15:58:55,396][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 15:58:55,892][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 15:58:56,390][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 15:58:56,886][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 15:58:57,382][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 15:58:57,880][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 15:58:58,377][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 15:58:58,874][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 15:58:59,374][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 15:58:59,873][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 15:59:00,369][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 15:59:00,863][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 15:59:01,358][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 15:59:01,855][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 15:59:02,358][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 15:59:02,854][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 15:59:03,351][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 15:59:03,848][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 15:59:04,344][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 15:59:04,842][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 15:59:05,339][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 15:59:05,837][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 15:59:06,334][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 15:59:06,831][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 15:59:07,329][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 15:59:07,826][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19369 tokens. [2026-03-25 15:59:09,014][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 13.98%, Current % of VRAM taken: 60.34%, Block Peak % of device VRAM: 61.63%, ΔTime: 00:01:09 [2026-03-25 15:59:09,743][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 15:59:09,745][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 15:59:09,746][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 15:59:10,443][__main__][INFO] - Iteration 13 took 1m 28s (16.19% Gen, 83.03% Train). Generation: 14s, Training: 1m 13s. Estimated remaining time: 73h 31m 6s. Estimated total time: 73h 55m 3s. Time estimates for 10 more iterations: 14m 47s, 100 more iterations: 2h 27m 50s, 500 more iterations: 12h 19m 10s. [2026-03-25 15:59:10,445][__main__][INFO] - Starting iteration 13. [2026-03-25 15:59:11,480][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 15:59:11,481][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 15:59:13,315][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:59:18,465][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls This proposal aims to maximize the allocation of high-value items for me, given my per-item values and Alice's differing values. Since hats are valuable for me and not as valuable for Alice, and books are valued similarly by both but not as highly by her, I propose taking all the hats while offering nothing for books and balls. This strategy focuses on the items with the highest differential value to me. did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 15:59:26,898][__main__][INFO] - Number of regex retries in iteration 13: 2 [2026-03-25 15:59:26,899][__main__][INFO] - agents played in iteration 13 are Bob, Alice [2026-03-25 15:59:28,820][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 15:59:29,892][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 15:59:31,499][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 15:59:32,628][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 15:59:33,127][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 15:59:34,132][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 15:59:35,001][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 15:59:35,500][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 15:59:36,003][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 15:59:36,502][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 15:59:37,000][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 15:59:37,499][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 15:59:37,996][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 15:59:38,500][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 15:59:38,997][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 15:59:39,495][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 15:59:39,992][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 15:59:40,489][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 15:59:40,983][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 15:59:41,479][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 15:59:41,977][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 15:59:42,475][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 15:59:42,971][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 15:59:43,466][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 15:59:43,960][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 15:59:44,455][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 15:59:44,953][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 15:59:45,584][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 15:59:46,084][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 15:59:46,583][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 15:59:47,083][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 15:59:47,581][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 15:59:48,080][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 15:59:48,579][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 15:59:49,077][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 15:59:49,573][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 15:59:50,070][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 15:59:50,567][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 15:59:51,064][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 15:59:51,560][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 15:59:52,063][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 15:59:52,559][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 15:59:53,056][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 15:59:53,555][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 15:59:54,053][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 15:59:54,550][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 15:59:55,047][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 15:59:55,543][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 15:59:56,040][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 15:59:56,538][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 15:59:57,034][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 15:59:57,533][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 15:59:58,031][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 15:59:58,529][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 15:59:59,025][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 15:59:59,523][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:00:00,020][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:00:00,517][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:00:01,013][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:00:01,510][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:00:02,005][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:00:02,502][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:00:02,999][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:00:03,496][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:00:03,992][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:00:04,489][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:00:04,989][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:00:05,487][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:00:05,984][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:00:06,482][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:00:06,979][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:00:07,478][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:00:07,979][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:00:08,479][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:00:08,975][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:00:09,474][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:00:09,968][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:00:10,464][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:00:10,959][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:00:11,456][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:00:11,955][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:00:12,452][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:00:12,947][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:00:13,441][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:00:13,938][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:00:14,433][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:00:14,928][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:00:15,422][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:00:15,917][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:00:16,412][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:00:16,908][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:00:17,411][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:00:17,912][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:00:18,415][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:00:18,914][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:00:19,414][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:00:19,912][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:00:20,410][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:00:20,906][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:00:21,402][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:00:21,902][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:00:22,400][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:00:22,897][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:00:23,393][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:00:23,890][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:00:24,385][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:00:24,883][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:00:25,379][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:00:25,876][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:00:26,375][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:00:26,873][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:00:27,371][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:00:27,867][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:00:28,365][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:00:28,861][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:00:29,357][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:00:29,854][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:00:30,350][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:00:30,846][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:00:31,342][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:00:31,839][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:00:32,336][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:00:32,832][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:00:33,329][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:00:33,825][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:00:34,322][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:00:34,819][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:00:35,314][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:00:35,809][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:00:36,305][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19620 tokens. [2026-03-25 16:00:37,841][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.03%, Current % of VRAM taken: 60.39%, Block Peak % of device VRAM: 61.88%, ΔTime: 00:01:07 [2026-03-25 16:00:38,568][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:00:38,571][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:00:38,572][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:00:39,256][__main__][INFO] - Iteration 14 took 1m 27s (17.57% Gen, 81.65% Train). Generation: 15s, Training: 1m 11s. Estimated remaining time: 72h 43m 25s. Estimated total time: 73h 8m 51s. Time estimates for 10 more iterations: 14m 37s, 100 more iterations: 2h 26m 17s, 500 more iterations: 12h 11m 28s. [2026-03-25 16:00:39,258][__main__][INFO] - Starting iteration 14. [2026-03-25 16:00:40,311][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:00:40,312][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:00:42,153][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 1 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:00:42,158][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:00:54,619][__main__][INFO] - Number of regex retries in iteration 14: 2 [2026-03-25 16:00:54,620][__main__][INFO] - agents played in iteration 14 are Bob, Alice [2026-03-25 16:00:56,792][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:00:57,858][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:00:59,474][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:01:00,605][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:01:01,102][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:01:02,103][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:01:02,600][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:01:03,098][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:01:03,595][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:01:04,093][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:01:04,593][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:01:05,088][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:01:05,584][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:01:06,083][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:01:06,579][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:01:07,077][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:01:07,573][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:01:08,075][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:01:08,574][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:01:09,073][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:01:09,572][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:01:10,070][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:01:10,567][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:01:11,065][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:01:11,562][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:01:12,059][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:01:12,558][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:01:13,053][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:01:13,549][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:01:14,047][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:01:14,544][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:01:15,039][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:01:15,536][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:01:16,034][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:01:17,047][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:01:17,545][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:01:18,042][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:01:18,541][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:01:19,039][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:01:19,537][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:01:20,035][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:01:20,532][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:01:21,030][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:01:21,526][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:01:22,023][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:01:22,520][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:01:23,017][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:01:23,514][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:01:24,012][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:01:24,511][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:01:25,008][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:01:25,507][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:01:26,002][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:01:26,502][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:01:27,002][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:01:27,501][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:01:28,000][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:01:28,498][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:01:28,998][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:01:29,497][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:01:29,995][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:01:30,493][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:01:30,992][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:01:31,489][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:01:31,986][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:01:32,483][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:01:32,980][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:01:33,478][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:01:33,976][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:01:34,475][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:01:34,973][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:01:35,471][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:01:35,969][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:01:36,467][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:01:36,963][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:01:37,460][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:01:37,958][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:01:38,455][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:01:38,952][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:01:39,447][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:01:39,943][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:01:40,440][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:01:40,937][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:01:41,435][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:01:41,934][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:01:42,432][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:01:42,929][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:01:43,426][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:01:43,923][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:01:44,420][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:01:44,919][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:01:45,417][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:01:45,914][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:01:46,412][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:01:46,909][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:01:47,406][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:01:47,902][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:01:48,399][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:01:48,898][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:01:49,395][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:01:49,895][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:01:50,394][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:01:50,893][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:01:51,391][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:01:51,887][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:01:52,383][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:01:52,880][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:01:53,377][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:01:53,874][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:01:54,373][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:01:54,869][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:01:55,365][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:01:55,863][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:01:56,362][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:01:56,859][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:01:57,357][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:01:57,851][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:01:58,348][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:01:58,846][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:01:59,699][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:02:00,196][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:02:00,693][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:02:01,190][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:02:01,686][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:02:02,182][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:02:02,677][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:02:03,175][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:02:03,671][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:02:04,166][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:02:04,662][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19575 tokens. [2026-03-25 16:02:05,819][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 13.99%, Current % of VRAM taken: 60.35%, Block Peak % of device VRAM: 61.82%, ΔTime: 00:01:07 [2026-03-25 16:02:06,545][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:02:06,548][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:02:06,549][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:02:07,237][__main__][INFO] - Iteration 15 took 1m 26s (16.46% Gen, 82.75% Train). Generation: 14s, Training: 1m 11s. Estimated remaining time: 71h 59m 24s. Estimated total time: 72h 26m 18s. Time estimates for 10 more iterations: 14m 29s, 100 more iterations: 2h 24m 52s, 500 more iterations: 12h 4m 23s. [2026-03-25 16:02:07,239][__main__][INFO] - Starting iteration 15. [2026-03-25 16:02:08,292][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:02:08,292][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:02:12,651][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:02:21,571][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:02:22,360][__main__][INFO] - Number of regex retries in iteration 15: 2 [2026-03-25 16:02:22,361][__main__][INFO] - agents played in iteration 15 are Bob, Alice [2026-03-25 16:02:24,762][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:02:25,831][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:02:27,445][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:02:28,577][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:02:29,076][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:02:30,076][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:02:30,575][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:02:31,089][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:02:31,586][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:02:32,084][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:02:32,581][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:02:33,082][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:02:33,578][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:02:34,075][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:02:34,572][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:02:35,070][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:02:35,568][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:02:36,072][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:02:36,568][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:02:37,063][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:02:37,559][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:02:38,054][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:02:38,551][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:02:39,047][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:02:39,542][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:02:40,038][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:02:40,533][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:02:41,029][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:02:41,526][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:02:42,022][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:02:42,517][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:02:43,014][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:02:43,512][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:02:44,008][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:02:44,503][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:02:44,999][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:02:45,493][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:02:45,990][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:02:46,485][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:02:46,980][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:02:47,476][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:02:47,972][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:02:48,468][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:02:48,963][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:02:49,460][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:02:49,958][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:02:50,454][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:02:50,951][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:02:51,446][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:02:51,942][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:02:52,438][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:02:52,934][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:02:53,429][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:02:53,925][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:02:54,420][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:02:54,916][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:02:55,412][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:02:55,909][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:02:56,405][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:02:56,903][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:02:57,399][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:02:57,896][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:02:58,393][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:02:58,896][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:02:59,393][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:02:59,890][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:03:00,387][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:03:00,884][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:03:01,382][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:03:01,879][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:03:02,376][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:03:02,874][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:03:03,372][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:03:03,869][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:03:04,367][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:03:04,866][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:03:05,362][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:03:05,858][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:03:06,353][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:03:06,851][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:03:07,347][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:03:07,845][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:03:08,342][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:03:08,837][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:03:09,333][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:03:09,830][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:03:10,325][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:03:10,821][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:03:11,317][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:03:11,815][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:03:12,312][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:03:12,808][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:03:13,304][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:03:13,801][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:03:14,298][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:03:14,794][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:03:15,294][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:03:15,791][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:03:16,286][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:03:16,781][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:03:17,276][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:03:17,771][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:03:18,266][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:03:18,762][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:03:19,257][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:03:19,753][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:03:20,248][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:03:20,744][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:03:21,241][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:03:21,737][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:03:22,234][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:03:22,732][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:03:23,229][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:03:23,725][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:03:24,221][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:03:24,717][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:03:25,212][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:03:25,708][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:03:26,204][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:03:26,702][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:03:27,198][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:03:27,695][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:03:28,191][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:03:28,688][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:03:29,184][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:03:29,679][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:03:30,182][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:03:30,678][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:03:31,174][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:03:31,672][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19538 tokens. [2026-03-25 16:03:32,917][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.02%, Current % of VRAM taken: 60.38%, Block Peak % of device VRAM: 61.82%, ΔTime: 00:01:07 [2026-03-25 16:03:33,653][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:03:33,655][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:03:33,657][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:03:34,342][__main__][INFO] - Iteration 16 took 1m 26s (16.35% Gen, 82.85% Train). Generation: 14s, Training: 1m 11s. Estimated remaining time: 71h 14m 12s. Estimated total time: 71h 42m 33s. Time estimates for 10 more iterations: 14m 20s, 100 more iterations: 2h 23m 25s, 500 more iterations: 11h 57m 5s. [2026-03-25 16:03:34,344][__main__][INFO] - Starting iteration 16. [2026-03-25 16:03:35,390][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:03:35,391][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:03:37,356][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:03:49,814][__main__][INFO] - Number of regex retries in iteration 16: 1 [2026-03-25 16:03:49,815][__main__][INFO] - agents played in iteration 16 are Bob, Alice [2026-03-25 16:03:51,874][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:03:52,942][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:03:54,556][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:03:55,682][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:03:56,177][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:03:57,167][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:03:58,169][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:03:59,061][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:03:59,556][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:04:00,051][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:04:00,548][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:04:01,654][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:04:02,152][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:04:02,649][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:04:03,146][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:04:04,133][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:04:04,630][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:04:05,128][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:04:06,034][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:04:06,532][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:04:07,633][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:04:08,129][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:04:08,628][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:04:09,124][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:04:09,622][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:04:10,376][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:04:10,873][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:04:11,370][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:04:11,867][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:04:12,363][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:04:12,859][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:04:13,356][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:04:13,854][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:04:14,350][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:04:14,847][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:04:15,345][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:04:15,842][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:04:16,340][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:04:16,838][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:04:17,335][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:04:17,833][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:04:18,330][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:04:18,826][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:04:19,321][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:04:19,818][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:04:20,313][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:04:20,813][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:04:21,310][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:04:21,806][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:04:22,303][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:04:22,797][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:04:23,293][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:04:23,787][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:04:24,282][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:04:24,777][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:04:25,274][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:04:25,777][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:04:26,274][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:04:26,773][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:04:27,272][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:04:27,770][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:04:28,267][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:04:28,763][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:04:29,260][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:04:29,757][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:04:30,253][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:04:30,750][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:04:31,245][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:04:31,741][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:04:32,237][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:04:32,733][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:04:33,229][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:04:33,725][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:04:34,220][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:04:34,716][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:04:35,213][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:04:35,710][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:04:36,207][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:04:36,704][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:04:37,201][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:04:37,699][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:04:38,196][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:04:38,695][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:04:39,194][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:04:39,694][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:04:40,194][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:04:40,693][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:04:41,193][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:04:41,691][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:04:42,192][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:04:42,687][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:04:43,183][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:04:43,679][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:04:44,177][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:04:44,675][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:04:45,173][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:04:45,672][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:04:46,169][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:04:46,667][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:04:47,163][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:04:47,660][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:04:48,158][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:04:48,655][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:04:49,152][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:04:49,653][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:04:50,152][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:04:50,649][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:04:51,143][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:04:51,639][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:04:52,135][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:04:52,632][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:04:53,128][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:04:53,624][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:04:54,120][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:04:54,614][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:04:55,111][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:04:55,606][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:04:56,100][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:04:56,595][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:04:57,090][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:04:57,586][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:04:58,080][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:04:58,578][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:04:59,077][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:04:59,576][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:05:00,074][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:05:00,574][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:05:01,072][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:05:01,569][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:05:02,066][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19641 tokens. [2026-03-25 16:05:03,210][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.03%, Current % of VRAM taken: 60.39%, Block Peak % of device VRAM: 61.94%, ΔTime: 00:01:10 [2026-03-25 16:05:03,934][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:05:03,936][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:05:03,938][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:05:04,616][__main__][INFO] - Iteration 17 took 1m 29s (16.17% Gen, 83.07% Train). Generation: 14s, Training: 1m 14s. Estimated remaining time: 73h 51m 27s. Estimated total time: 74h 21m 18s. Time estimates for 10 more iterations: 14m 52s, 100 more iterations: 2h 28m 42s, 500 more iterations: 12h 23m 33s. [2026-03-25 16:05:04,618][__main__][INFO] - Starting iteration 17. [2026-03-25 16:05:05,681][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:05:05,682][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:05:17,979][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:05:20,402][__main__][INFO] - Number of regex retries in iteration 17: 1 [2026-03-25 16:05:20,403][__main__][INFO] - agents played in iteration 17 are Bob, Alice [2026-03-25 16:05:23,034][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:05:24,104][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:05:25,716][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:05:26,842][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:05:27,342][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:05:27,840][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:05:28,480][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:05:28,978][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:05:29,476][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:05:29,975][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:05:30,473][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:05:30,970][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:05:31,467][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:05:31,963][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:05:32,460][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:05:32,958][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:05:33,454][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:05:33,951][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:05:34,446][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:05:34,944][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:05:35,439][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:05:35,935][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:05:36,434][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:05:36,933][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:05:37,430][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:05:37,926][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:05:38,423][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:05:38,921][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:05:39,420][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:05:39,918][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:05:40,415][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:05:40,918][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:05:41,417][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:05:41,915][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:05:42,413][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:05:42,911][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:05:43,410][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:05:43,907][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:05:44,405][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:05:44,904][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:05:45,403][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:05:45,901][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:05:46,401][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:05:46,900][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:05:47,397][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:05:47,895][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:05:48,394][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:05:48,891][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:05:49,390][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:05:49,887][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:05:50,383][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:05:50,880][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:05:51,376][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:05:51,874][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:05:52,371][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:05:52,866][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:05:53,362][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:05:53,857][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:05:54,354][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:05:54,852][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:05:55,347][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:05:55,844][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:05:56,340][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:05:56,837][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:05:57,335][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:05:57,832][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:05:58,333][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:05:58,835][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:05:59,338][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:05:59,835][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:06:00,334][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:06:00,831][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:06:01,329][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:06:01,830][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:06:02,325][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:06:02,822][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:06:03,319][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:06:03,816][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:06:04,312][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:06:04,809][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:06:05,306][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:06:05,802][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:06:06,298][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:06:06,794][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:06:07,291][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:06:07,787][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:06:08,283][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:06:08,779][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:06:09,277][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:06:09,776][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:06:10,275][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:06:10,773][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:06:11,274][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:06:11,773][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:06:12,272][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:06:12,769][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:06:13,267][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:06:13,765][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:06:14,261][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:06:14,759][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:06:15,258][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:06:15,755][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:06:16,253][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:06:16,752][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:06:17,251][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:06:17,748][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:06:18,252][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:06:18,756][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:06:19,254][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:06:19,752][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:06:20,252][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:06:20,750][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:06:21,248][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:06:21,747][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:06:22,244][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:06:22,739][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:06:23,234][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:06:23,730][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:06:24,224][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:06:24,719][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:06:25,214][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:06:25,709][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:06:26,207][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:06:26,703][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:06:27,200][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:06:27,698][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:06:28,196][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:06:28,694][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:06:29,194][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:06:29,694][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19855 tokens. [2026-03-25 16:06:30,786][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.10%, Current % of VRAM taken: 60.46%, Block Peak % of device VRAM: 62.04%, ΔTime: 00:01:06 [2026-03-25 16:06:31,508][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:06:31,510][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:06:31,512][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:06:32,197][__main__][INFO] - Iteration 18 took 1m 26s (17.02% Gen, 82.19% Train). Generation: 14s, Training: 1m 11s. Estimated remaining time: 71h 34m 30s. Estimated total time: 72h 5m 49s. Time estimates for 10 more iterations: 14m 25s, 100 more iterations: 2h 24m 11s, 500 more iterations: 12h 0m 58s. [2026-03-25 16:06:32,199][__main__][INFO] - Starting iteration 18. [2026-03-25 16:06:33,255][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:06:33,256][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:06:35,098][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:06:47,783][__main__][INFO] - Number of regex retries in iteration 18: 1 [2026-03-25 16:06:47,785][__main__][INFO] - agents played in iteration 18 are Bob, Alice [2026-03-25 16:06:49,745][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:06:50,812][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:06:52,423][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:06:53,552][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:06:54,052][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:06:54,551][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:06:55,056][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:06:55,554][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:06:56,051][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:06:56,548][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:06:57,044][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:06:57,540][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:06:58,037][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:06:58,534][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:06:59,032][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:06:59,529][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:07:00,026][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:07:00,523][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:07:01,283][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:07:01,781][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:07:02,279][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:07:02,782][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:07:03,281][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:07:03,780][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:07:04,280][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:07:04,780][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:07:05,277][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:07:05,775][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:07:06,275][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:07:06,773][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:07:07,274][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:07:07,772][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:07:08,270][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:07:08,767][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:07:09,264][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:07:09,762][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:07:10,260][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:07:10,759][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:07:11,257][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:07:11,756][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:07:12,254][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:07:12,753][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:07:13,249][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:07:13,745][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:07:14,241][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:07:14,737][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:07:15,235][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:07:15,730][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:07:16,226][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:07:16,722][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:07:17,220][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:07:17,718][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:07:18,216][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:07:18,713][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:07:19,210][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:07:19,707][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:07:20,205][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:07:20,701][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:07:21,199][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:07:21,696][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:07:22,195][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:07:22,693][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:07:23,193][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:07:23,690][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:07:24,189][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:07:24,686][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:07:25,184][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:07:25,685][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:07:26,183][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:07:26,680][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:07:27,181][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:07:27,678][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:07:28,177][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:07:28,676][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:07:29,174][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:07:29,674][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:07:30,172][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:07:30,669][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:07:31,165][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:07:31,661][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:07:32,156][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:07:32,657][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:07:33,157][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:07:33,654][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:07:34,154][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:07:34,654][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:07:35,151][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:07:35,646][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:07:36,145][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:07:36,644][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:07:37,140][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:07:37,637][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:07:38,137][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:07:38,636][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:07:39,136][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:07:39,633][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:07:40,131][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:07:40,627][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:07:41,125][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:07:41,624][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:07:42,124][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:07:42,623][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:07:43,120][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:07:43,618][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:07:44,116][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:07:44,615][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:07:45,112][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:07:45,608][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:07:46,104][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:07:46,600][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:07:47,098][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:07:47,595][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:07:48,093][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:07:48,591][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:07:49,089][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:07:49,586][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:07:50,083][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:07:50,580][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:07:51,077][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:07:51,576][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:07:52,074][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:07:52,573][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:07:53,073][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:07:53,570][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:07:54,067][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:07:54,565][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:07:55,062][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:07:55,559][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:07:56,058][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:07:56,556][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19900 tokens. [2026-03-25 16:07:57,905][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.09%, Current % of VRAM taken: 60.44%, Block Peak % of device VRAM: 61.92%, ΔTime: 00:01:07 [2026-03-25 16:07:58,629][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:07:58,631][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:07:58,633][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:07:59,330][__main__][INFO] - Iteration 19 took 1m 26s (16.88% Gen, 82.31% Train). Generation: 14s, Training: 1m 10s. Estimated remaining time: 71h 11m 1s. Estimated total time: 71h 43m 47s. Time estimates for 10 more iterations: 14m 20s, 100 more iterations: 2h 23m 27s, 500 more iterations: 11h 57m 17s. [2026-03-25 16:07:59,333][__main__][INFO] - Starting iteration 19. [2026-03-25 16:08:00,374][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:08:00,375][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:08:02,241][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:08:07,101][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls Given Alice's per-item values, she will likely propose to keep all the books and balls since those items are more valuable to her. This means I should focus on the hats, as they are most valuable to me. By proposing to take all the hats, I maximize my value from this round, assuming Alice will distribute the books and balls in her favor. did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:08:09,855][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:08:15,271][__main__][INFO] - Number of regex retries in iteration 19: 3 [2026-03-25 16:08:15,272][__main__][INFO] - agents played in iteration 19 are Bob, Alice [2026-03-25 16:08:17,736][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:08:18,802][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:08:20,420][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:08:21,547][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:08:22,043][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:08:23,047][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:08:23,544][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:08:24,040][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:08:24,538][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:08:25,036][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:08:25,785][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:08:26,647][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:08:27,146][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:08:27,645][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:08:28,143][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:08:29,264][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:08:29,763][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:08:30,261][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:08:30,757][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:08:31,254][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:08:31,753][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:08:32,253][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:08:32,752][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:08:33,249][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:08:33,747][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:08:34,244][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:08:34,737][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:08:35,232][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:08:35,726][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:08:36,220][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:08:36,716][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:08:37,211][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:08:37,706][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:08:38,202][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:08:38,700][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:08:39,199][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:08:39,698][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:08:40,200][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:08:40,698][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:08:41,197][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:08:41,696][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:08:42,195][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:08:42,694][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:08:43,192][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:08:43,689][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:08:44,185][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:08:44,682][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:08:45,179][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:08:45,675][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:08:46,173][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:08:46,673][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:08:47,172][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:08:47,669][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:08:48,168][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:08:48,666][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:08:49,172][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:08:49,670][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:08:50,168][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:08:50,664][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:08:51,161][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:08:51,658][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:08:52,155][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:08:52,653][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:08:53,149][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:08:53,645][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:08:54,142][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:08:54,641][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:08:55,138][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:08:55,635][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:08:56,133][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:08:56,630][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:08:57,126][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:08:57,623][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:08:58,121][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:08:58,619][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:08:59,118][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:08:59,751][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:09:00,250][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:09:00,747][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:09:01,245][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:09:01,744][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:09:02,242][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:09:02,738][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:09:03,236][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:09:03,733][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:09:04,230][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:09:04,728][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:09:05,225][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:09:05,722][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:09:06,219][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:09:06,714][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:09:07,209][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:09:07,705][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:09:08,199][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:09:08,693][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:09:09,188][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:09:09,681][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:09:10,176][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:09:10,674][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:09:11,176][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:09:11,674][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:09:12,174][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:09:12,672][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:09:13,169][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:09:13,666][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:09:14,163][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:09:14,660][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:09:15,156][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:09:15,653][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:09:16,150][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:09:16,646][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:09:17,142][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:09:17,638][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:09:18,134][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:09:18,632][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:09:19,129][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:09:19,625][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:09:20,123][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:09:20,620][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:09:21,118][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:09:21,615][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:09:22,113][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:09:22,610][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:09:23,107][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:09:23,604][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:09:24,101][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:09:24,599][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:09:25,097][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:09:25,594][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:09:26,092][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19753 tokens. [2026-03-25 16:09:27,644][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.01%, Current % of VRAM taken: 60.37%, Block Peak % of device VRAM: 61.84%, ΔTime: 00:01:08 [2026-03-25 16:09:28,371][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:09:28,373][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:09:28,374][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:09:29,032][__main__][INFO] - Iteration 20 took 1m 28s (16.80% Gen, 82.45% Train). Generation: 14s, Training: 1m 13s. Estimated remaining time: 73h 18m 38s. Estimated total time: 73h 52m 54s. Time estimates for 10 more iterations: 14m 46s, 100 more iterations: 2h 27m 45s, 500 more iterations: 12h 18m 49s. [2026-03-25 16:09:29,034][__main__][INFO] - Starting iteration 20. [2026-03-25 16:09:30,115][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:09:30,116][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:09:37,175][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls This proposal aims to maximize the amount of hats I can keep, as they offer a higher value to me compared to the other items. Given Bob's per-item values, he values books more than hats. Therefore, proposing to take all the hats ensures I get the maximum possible value from this round, without leaving any items to potentially be contested with books or balls. did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:09:45,674][__main__][INFO] - Number of regex retries in iteration 20: 1 [2026-03-25 16:09:45,675][__main__][INFO] - agents played in iteration 20 are Bob, Alice [2026-03-25 16:09:47,474][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:09:48,535][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:09:50,157][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:09:51,284][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:09:52,032][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:09:52,917][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:09:53,415][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:09:53,913][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:09:54,411][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:09:54,906][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:09:55,404][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:09:55,904][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:09:56,402][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:09:56,899][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:09:57,396][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:09:57,894][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:09:58,390][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:09:58,886][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:09:59,385][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:09:59,883][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:10:00,381][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:10:00,879][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:10:01,378][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:10:01,876][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:10:02,374][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:10:02,871][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:10:03,368][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:10:03,864][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:10:04,360][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:10:04,859][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:10:05,358][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:10:05,855][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:10:06,353][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:10:06,851][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:10:07,350][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:10:07,848][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:10:08,347][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:10:08,843][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:10:09,341][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:10:09,840][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:10:10,339][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:10:10,836][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:10:11,335][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:10:11,833][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:10:12,332][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:10:12,830][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:10:13,328][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:10:13,827][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:10:14,325][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:10:14,824][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:10:15,321][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:10:15,818][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:10:16,313][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:10:16,809][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:10:17,305][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:10:17,800][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:10:18,298][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:10:18,797][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:10:19,294][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:10:19,794][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:10:20,293][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:10:20,791][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:10:21,660][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:10:22,157][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:10:22,655][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:10:23,153][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:10:23,650][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:10:24,147][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:10:24,645][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:10:25,144][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:10:25,640][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:10:26,138][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:10:26,636][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:10:27,133][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:10:27,633][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:10:28,132][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:10:28,629][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:10:29,127][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:10:29,623][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:10:30,119][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:10:30,616][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:10:31,114][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:10:31,614][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:10:32,113][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:10:32,613][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:10:33,111][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:10:33,609][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:10:34,107][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:10:34,605][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:10:35,104][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:10:35,601][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:10:36,099][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:10:36,598][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:10:37,098][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:10:37,596][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:10:38,096][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:10:38,594][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:10:39,093][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:10:39,591][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:10:40,091][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:10:40,592][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:10:41,089][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:10:41,587][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:10:42,086][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:10:42,583][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:10:43,082][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:10:43,580][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:10:44,079][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:10:44,579][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:10:45,077][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:10:45,576][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:10:46,074][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:10:46,573][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:10:47,073][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:10:47,572][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:10:48,069][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:10:48,565][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:10:49,061][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:10:49,558][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:10:50,054][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:10:50,551][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:10:51,047][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:10:51,544][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:10:52,041][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:10:52,543][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:10:53,040][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:10:53,541][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:10:54,038][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:10:54,535][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:10:55,032][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19861 tokens. [2026-03-25 16:10:56,514][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.00%, Current % of VRAM taken: 60.36%, Block Peak % of device VRAM: 61.85%, ΔTime: 00:01:07 [2026-03-25 16:10:57,239][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:10:57,242][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:10:57,243][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:10:57,895][__main__][INFO] - Iteration 21 took 1m 27s (17.73% Gen, 81.53% Train). Generation: 15s, Training: 1m 11s. Estimated remaining time: 72h 33m 14s. Estimated total time: 73h 8m 59s. Time estimates for 10 more iterations: 14m 37s, 100 more iterations: 2h 26m 17s, 500 more iterations: 12h 11m 29s. [2026-03-25 16:10:57,897][__main__][INFO] - Starting iteration 21. [2026-03-25 16:10:58,992][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:10:58,993][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:11:04,083][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 0 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:11:05,747][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls Given the per-item values, my strategy here is to prioritize items with higher values for me, which are hats. Since Alice values books more and balls equally, she is likely to propose higher amounts for books and balls. By proposing to take all the hats, I maximize my points from this round, assuming the total amount of hats I propose does not exceed their quantity. did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:11:12,753][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls Given Alice's per-item values, she values hats much less than I do, and books and balls more than I do. To maximize my points, I should propose to take all the hats since they align with my values. I should avoid taking any books or balls as they would hurt my total points since Alice values them highly. did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 2/3 [2026-03-25 16:11:15,249][__main__][INFO] - Number of regex retries in iteration 21: 3 [2026-03-25 16:11:15,250][__main__][INFO] - agents played in iteration 21 are Bob, Alice [2026-03-25 16:11:17,225][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:11:18,286][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:11:19,904][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:11:21,651][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:11:22,659][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:11:23,520][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:11:24,019][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:11:24,518][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:11:25,016][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:11:25,515][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:11:26,013][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:11:26,510][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:11:27,007][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:11:27,504][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:11:28,002][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:11:28,498][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:11:28,996][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:11:29,496][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:11:29,994][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:11:30,493][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:11:30,989][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:11:31,486][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:11:31,984][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:11:32,481][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:11:32,978][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:11:33,476][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:11:33,973][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:11:34,469][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:11:34,965][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:11:35,461][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:11:35,958][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:11:36,454][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:11:36,953][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:11:37,449][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:11:37,944][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:11:38,441][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:11:38,939][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:11:39,436][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:11:39,932][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:11:40,428][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:11:40,924][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:11:41,422][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:11:41,921][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:11:42,695][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:11:43,193][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:11:43,691][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:11:44,194][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:11:44,692][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:11:45,191][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:11:45,690][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:11:46,194][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:11:47,064][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:11:47,562][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:11:48,062][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:11:48,561][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:11:49,061][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:11:49,560][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:11:50,061][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:11:50,557][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:11:51,053][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:11:51,550][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:11:52,047][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:11:52,543][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:11:53,039][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:11:53,537][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:11:54,033][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:11:54,530][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:11:55,028][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:11:55,614][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:11:56,114][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:11:56,613][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:11:57,112][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:11:57,610][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:11:58,108][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:11:58,608][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:11:59,107][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:11:59,605][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:12:00,104][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:12:00,603][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:12:01,101][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:12:01,599][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:12:02,098][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:12:02,596][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:12:03,096][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:12:03,595][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:12:04,093][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:12:04,591][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:12:05,089][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:12:05,587][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:12:06,088][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:12:06,584][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:12:07,080][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:12:07,578][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:12:08,074][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:12:08,572][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:12:09,067][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:12:09,563][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:12:10,060][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:12:10,558][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:12:11,055][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:12:11,555][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:12:12,055][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:12:12,550][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:12:13,047][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:12:13,545][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:12:14,042][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:12:14,541][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:12:15,040][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:12:15,539][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:12:16,038][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:12:16,537][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:12:17,035][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:12:17,534][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:12:18,033][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:12:19,138][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:12:20,154][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:12:20,653][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:12:21,154][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:12:21,655][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:12:22,155][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:12:22,654][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:12:23,156][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:12:23,652][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:12:24,148][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:12:24,643][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:12:25,141][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:12:25,638][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:12:26,134][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:12:26,631][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:12:27,129][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19795 tokens. [2026-03-25 16:12:28,864][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.06%, Current % of VRAM taken: 60.42%, Block Peak % of device VRAM: 62.13%, ΔTime: 00:01:10 [2026-03-25 16:12:29,587][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:12:29,589][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:12:29,590][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:12:30,263][__main__][INFO] - Iteration 22 took 1m 31s (17.81% Gen, 81.45% Train). Generation: 16s, Training: 1m 14s. Estimated remaining time: 75h 26m 16s. Estimated total time: 76h 3m 32s. Time estimates for 10 more iterations: 15m 12s, 100 more iterations: 2h 32m 7s, 500 more iterations: 12h 40m 35s. [2026-03-25 16:12:30,265][__main__][INFO] - Starting iteration 22. [2026-03-25 16:12:31,335][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:12:31,335][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:12:46,050][__main__][INFO] - Number of regex retries in iteration 22: 0 [2026-03-25 16:12:46,050][__main__][INFO] - agents played in iteration 22 are Bob, Alice [2026-03-25 16:12:48,697][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:12:49,765][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:12:51,377][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:12:52,499][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:12:53,253][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:12:54,135][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:12:54,633][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:12:55,129][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:12:55,626][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:12:56,123][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:12:56,743][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:12:57,604][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:12:58,103][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:12:59,222][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:13:00,222][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:13:00,722][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:13:01,223][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:13:01,723][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:13:02,219][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:13:02,718][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:13:03,215][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:13:03,713][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:13:04,210][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:13:04,707][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:13:05,205][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:13:05,701][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:13:06,200][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:13:06,700][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:13:07,200][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:13:07,700][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:13:08,200][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:13:08,700][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:13:09,200][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:13:09,700][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:13:10,198][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:13:10,699][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:13:11,198][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:13:11,698][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:13:12,197][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:13:12,699][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:13:13,197][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:13:13,699][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:13:14,197][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:13:14,695][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:13:15,768][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:13:16,266][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:13:16,764][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:13:17,262][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:13:17,761][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:13:18,259][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:13:18,756][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:13:19,254][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:13:19,750][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:13:20,247][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:13:20,743][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:13:21,239][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:13:21,736][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:13:22,234][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:13:22,732][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:13:23,228][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:13:23,726][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:13:24,224][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:13:24,723][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:13:25,221][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:13:25,720][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:13:26,218][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:13:26,715][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:13:27,212][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:13:27,708][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:13:28,205][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:13:28,703][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:13:29,201][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:13:29,698][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:13:30,197][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:13:30,695][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:13:31,194][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:13:31,693][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:13:32,194][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:13:33,209][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:13:34,156][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:13:34,657][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:13:35,158][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:13:35,654][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:13:36,151][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:13:36,648][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:13:37,146][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:13:37,643][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:13:38,138][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:13:38,634][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:13:39,134][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:13:39,634][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:13:40,135][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:13:40,635][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:13:41,134][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:13:41,633][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:13:42,131][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:13:42,628][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:13:43,129][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:13:43,627][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:13:44,127][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:13:44,625][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:13:45,124][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:13:45,621][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:13:46,122][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:13:46,621][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:13:47,122][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:13:47,620][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:13:48,121][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:13:48,877][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:13:49,375][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:13:49,873][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:13:50,371][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:13:50,872][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:13:51,369][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:13:51,865][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:13:52,361][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:13:52,857][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:13:53,354][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:13:53,851][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:13:54,347][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:13:54,844][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:13:55,341][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:13:55,841][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:13:56,338][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:13:56,836][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:13:57,335][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:13:57,835][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:13:58,334][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:13:58,832][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:13:59,329][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20117 tokens. [2026-03-25 16:14:00,332][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.10%, Current % of VRAM taken: 60.46%, Block Peak % of device VRAM: 62.12%, ΔTime: 00:01:10 [2026-03-25 16:14:01,058][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:14:01,061][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:14:01,062][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:14:01,742][__main__][INFO] - Iteration 23 took 1m 30s (16.28% Gen, 82.97% Train). Generation: 14s, Training: 1m 15s. Estimated remaining time: 74h 41m 33s. Estimated total time: 75h 20m 22s. Time estimates for 10 more iterations: 15m 4s, 100 more iterations: 2h 30m 40s, 500 more iterations: 12h 33m 23s. [2026-03-25 16:14:01,744][__main__][INFO] - Starting iteration 23. [2026-03-25 16:14:02,807][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:14:02,807][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:14:17,938][__main__][INFO] - Number of regex retries in iteration 23: 0 [2026-03-25 16:14:17,939][__main__][INFO] - agents played in iteration 23 are Bob, Alice [2026-03-25 16:14:20,175][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:14:21,244][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:14:22,858][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:14:23,978][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:14:24,750][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:14:25,602][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:14:26,098][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:14:26,595][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:14:27,093][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:14:27,591][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:14:28,088][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:14:29,096][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:14:29,594][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:14:30,701][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:14:31,199][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:14:31,696][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:14:32,195][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:14:32,694][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:14:33,191][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:14:33,687][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:14:34,182][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:14:34,677][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:14:35,173][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:14:35,669][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:14:36,164][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:14:36,659][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:14:37,157][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:14:37,822][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:14:38,672][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:14:39,170][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:14:39,671][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:14:40,169][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:14:40,672][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:14:41,287][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:14:41,784][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:14:42,281][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:14:42,779][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:14:43,276][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:14:43,774][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:14:44,270][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:14:44,767][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:14:45,262][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:14:45,759][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:14:46,258][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:14:46,756][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:14:47,255][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:14:47,753][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:14:48,250][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:14:48,748][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:14:49,248][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:14:49,745][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:14:50,241][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:14:50,738][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:14:51,236][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:14:51,734][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:14:52,230][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:14:52,728][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:14:53,225][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:14:53,722][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:14:54,219][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:14:54,717][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:14:55,213][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:14:55,713][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:14:56,210][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:14:56,708][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:14:57,206][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:14:57,702][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:14:58,199][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:14:58,697][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:14:59,197][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:14:59,695][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:15:00,193][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:15:00,690][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:15:01,187][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:15:01,684][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:15:02,182][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:15:02,679][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:15:03,178][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:15:03,676][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:15:04,174][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:15:04,671][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:15:05,168][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:15:05,663][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:15:06,160][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:15:06,656][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:15:07,152][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:15:07,649][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:15:08,146][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:15:08,642][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:15:09,138][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:15:09,636][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:15:10,136][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:15:10,636][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:15:11,134][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:15:11,635][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:15:12,135][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:15:12,635][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:15:13,135][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:15:13,632][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:15:14,129][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:15:14,626][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:15:15,123][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:15:15,620][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:15:16,118][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:15:16,615][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:15:17,111][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:15:17,610][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:15:18,108][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:15:18,608][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:15:19,106][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:15:19,605][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:15:20,102][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:15:20,601][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:15:21,099][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:15:21,597][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:15:22,095][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:15:22,593][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:15:23,090][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:15:23,586][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:15:24,083][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:15:24,580][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:15:25,076][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:15:25,574][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:15:26,072][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:15:26,569][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:15:27,066][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:15:27,563][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:15:28,059][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:15:28,556][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:15:29,054][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 19891 tokens. [2026-03-25 16:15:30,081][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.04%, Current % of VRAM taken: 60.40%, Block Peak % of device VRAM: 62.15%, ΔTime: 00:01:08 [2026-03-25 16:15:30,804][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:15:30,807][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:15:30,808][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:15:31,491][__main__][INFO] - Iteration 24 took 1m 28s (17.06% Gen, 82.17% Train). Generation: 15s, Training: 1m 12s. Estimated remaining time: 73h 13m 56s. Estimated total time: 73h 54m 14s. Time estimates for 10 more iterations: 14m 46s, 100 more iterations: 2h 27m 48s, 500 more iterations: 12h 19m 2s. [2026-03-25 16:15:31,493][__main__][INFO] - Starting iteration 24. [2026-03-25 16:15:32,549][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:15:32,549][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:15:36,814][mllm.models.large_language_model_local][WARNING] - Response Proposal: 9 hats, 0 books, 11 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:15:47,165][__main__][INFO] - Number of regex retries in iteration 24: 1 [2026-03-25 16:15:47,166][__main__][INFO] - agents played in iteration 24 are Bob, Alice [2026-03-25 16:15:49,039][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:15:50,112][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:15:51,722][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:15:52,848][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:15:53,346][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:15:53,850][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:15:54,471][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:15:54,970][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:15:55,468][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:15:56,087][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:15:57,083][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:15:57,581][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:15:58,082][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:15:58,840][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:15:59,339][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:15:59,839][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:16:00,341][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:16:00,840][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:16:01,339][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:16:01,840][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:16:02,338][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:16:02,838][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:16:03,336][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:16:03,836][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:16:04,336][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:16:04,836][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:16:05,333][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:16:05,830][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:16:06,324][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:16:06,822][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:16:07,320][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:16:07,817][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:16:08,315][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:16:08,812][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:16:09,311][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:16:09,812][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:16:10,310][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:16:10,810][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:16:11,313][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:16:11,812][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:16:12,312][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:16:12,811][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:16:13,310][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:16:13,809][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:16:14,307][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:16:14,804][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:16:15,302][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:16:15,801][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:16:16,300][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:16:16,799][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:16:17,298][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:16:17,797][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:16:18,298][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:16:18,797][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:16:19,295][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:16:19,795][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:16:20,294][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:16:20,791][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:16:21,287][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:16:21,786][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:16:22,284][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:16:22,781][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:16:23,280][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:16:23,778][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:16:24,275][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:16:24,773][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:16:25,272][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:16:25,770][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:16:26,267][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:16:26,763][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:16:27,260][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:16:27,758][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:16:28,255][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:16:28,754][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:16:29,254][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:16:29,753][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:16:30,255][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:16:31,054][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:16:31,553][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:16:32,052][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:16:32,553][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:16:33,054][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:16:33,553][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:16:34,054][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:16:34,554][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:16:35,054][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:16:35,553][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:16:36,052][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:16:36,551][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:16:37,050][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:16:37,547][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:16:38,045][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:16:38,541][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:16:39,039][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:16:39,537][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:16:40,035][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:16:40,534][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:16:41,032][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:16:41,532][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:16:42,032][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:16:42,533][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:16:43,034][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:16:43,535][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:16:44,033][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:16:44,531][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:16:45,031][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:16:45,529][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:16:46,028][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:16:46,528][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:16:47,026][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:16:47,526][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:16:48,025][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:16:48,525][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:16:49,023][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:16:49,523][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:16:50,022][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:16:50,522][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:16:51,022][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:16:51,520][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:16:52,020][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:16:52,519][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:16:53,018][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:16:53,516][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:16:54,016][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:16:54,515][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:16:55,014][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:16:55,515][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:16:56,013][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:16:56,511][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:16:57,009][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20185 tokens. [2026-03-25 16:16:58,074][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.06%, Current % of VRAM taken: 60.42%, Block Peak % of device VRAM: 61.99%, ΔTime: 00:01:07 [2026-03-25 16:16:58,807][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:16:58,809][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:16:58,811][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:16:59,510][__main__][INFO] - Iteration 25 took 1m 26s (16.81% Gen, 82.39% Train). Generation: 14s, Training: 1m 11s. Estimated remaining time: 71h 46m 21s. Estimated total time: 72h 28m 7s. Time estimates for 10 more iterations: 14m 29s, 100 more iterations: 2h 24m 56s, 500 more iterations: 12h 4m 41s. [2026-03-25 16:16:59,512][__main__][INFO] - Starting iteration 25. [2026-03-25 16:17:00,548][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:17:00,549][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:17:04,016][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:17:14,929][__main__][INFO] - Number of regex retries in iteration 25: 1 [2026-03-25 16:17:14,930][__main__][INFO] - agents played in iteration 25 are Bob, Alice [2026-03-25 16:17:17,029][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:17:18,099][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:17:19,710][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:17:20,829][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:17:21,601][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:17:22,101][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:17:22,600][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:17:23,102][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:17:23,601][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:17:24,100][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:17:24,599][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:17:25,097][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:17:25,595][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:17:26,093][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:17:26,593][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:17:27,090][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:17:27,587][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:17:28,084][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:17:28,582][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:17:29,079][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:17:29,577][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:17:30,075][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:17:30,573][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:17:31,070][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:17:31,568][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:17:32,066][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:17:32,564][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:17:33,063][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:17:33,563][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:17:34,062][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:17:34,562][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:17:35,060][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:17:35,559][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:17:36,059][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:17:36,558][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:17:37,057][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:17:37,557][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:17:38,056][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:17:38,554][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:17:39,053][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:17:39,554][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:17:40,051][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:17:40,559][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:17:41,058][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:17:41,558][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:17:42,057][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:17:42,557][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:17:43,057][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:17:43,556][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:17:44,056][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:17:44,564][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:17:45,065][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:17:45,566][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:17:46,072][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:17:46,570][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:17:47,074][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:17:47,576][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:17:48,077][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:17:48,576][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:17:49,078][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:17:49,579][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:17:50,077][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:17:50,578][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:17:51,077][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:17:51,576][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:17:52,078][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:17:52,578][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:17:53,079][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:17:53,830][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:17:54,329][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:17:54,829][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:17:55,332][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:17:55,830][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:17:56,330][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:17:56,828][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:17:57,326][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:17:57,823][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:17:58,320][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:17:58,819][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:17:59,318][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:17:59,816][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:18:00,315][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:18:00,813][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:18:01,311][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:18:01,810][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:18:02,307][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:18:02,805][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:18:03,302][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:18:03,801][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:18:04,299][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:18:04,799][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:18:05,298][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:18:05,796][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:18:06,296][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:18:06,797][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:18:07,296][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:18:07,796][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:18:08,296][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:18:08,798][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:18:09,296][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:18:09,795][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:18:10,297][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:18:10,795][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:18:11,297][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:18:11,800][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:18:12,298][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:18:12,798][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:18:13,297][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:18:13,800][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:18:14,298][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:18:14,798][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:18:15,297][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:18:15,797][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:18:16,296][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:18:16,798][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:18:17,299][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:18:17,800][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:18:18,301][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:18:18,801][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:18:19,302][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:18:19,801][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:18:20,301][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:18:20,800][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:18:21,300][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:18:21,799][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:18:22,297][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:18:22,797][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:18:23,299][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:18:23,798][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:18:24,298][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20236 tokens. [2026-03-25 16:18:26,076][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.13%, Current % of VRAM taken: 60.48%, Block Peak % of device VRAM: 62.21%, ΔTime: 00:01:07 [2026-03-25 16:18:26,807][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:18:26,810][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:18:26,811][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:18:27,509][__main__][INFO] - Iteration 26 took 1m 26s (16.54% Gen, 82.66% Train). Generation: 14s, Training: 1m 11s. Estimated remaining time: 71h 44m 52s. Estimated total time: 72h 28m 6s. Time estimates for 10 more iterations: 14m 29s, 100 more iterations: 2h 24m 56s, 500 more iterations: 12h 4m 41s. [2026-03-25 16:18:27,512][__main__][INFO] - Starting iteration 26. [2026-03-25 16:18:28,546][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:18:28,546][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:18:42,134][__main__][INFO] - Number of regex retries in iteration 26: 0 [2026-03-25 16:18:42,136][__main__][INFO] - agents played in iteration 26 are Bob, Alice [2026-03-25 16:18:44,160][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:18:45,238][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:18:46,844][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:18:47,972][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:18:48,738][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:18:49,592][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:18:50,464][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:18:50,967][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:18:51,464][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:18:52,072][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:18:52,569][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:18:53,066][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:18:53,562][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:18:54,060][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:18:54,566][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:18:55,065][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:18:55,563][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:18:56,573][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:18:57,464][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:18:58,308][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:18:58,806][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:18:59,306][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:18:59,815][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:19:00,315][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:19:00,927][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:19:01,426][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:19:01,925][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:19:02,423][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:19:02,921][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:19:03,419][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:19:03,917][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:19:04,416][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:19:04,913][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:19:05,412][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:19:05,912][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:19:06,411][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:19:06,910][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:19:07,409][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:19:07,907][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:19:08,407][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:19:08,906][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:19:09,404][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:19:09,902][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:19:10,397][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:19:10,894][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:19:11,390][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:19:11,886][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:19:12,380][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:19:12,876][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:19:13,372][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:19:13,869][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:19:14,365][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:19:14,861][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:19:15,358][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:19:15,856][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:19:16,352][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:19:16,848][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:19:17,345][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:19:17,844][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:19:18,342][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:19:18,838][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:19:19,336][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:19:19,834][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:19:20,333][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:19:20,830][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:19:21,328][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:19:21,824][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:19:22,318][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:19:22,816][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:19:23,313][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:19:23,812][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:19:24,308][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:19:24,805][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:19:25,303][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:19:25,799][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:19:26,297][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:19:26,794][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:19:27,290][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:19:27,786][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:19:28,282][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:19:28,780][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:19:29,280][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:19:30,415][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:19:30,914][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:19:31,411][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:19:31,909][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:19:32,409][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:19:32,906][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:19:33,405][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:19:33,903][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:19:34,402][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:19:34,900][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:19:35,398][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:19:35,898][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:19:36,397][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:19:36,896][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:19:37,394][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:19:37,894][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:19:38,395][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:19:39,257][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:19:39,755][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:19:40,255][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:19:40,754][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:19:41,255][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:19:41,755][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:19:42,254][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:19:42,749][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:19:43,245][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:19:43,740][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:19:44,235][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:19:44,729][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:19:45,224][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:19:45,721][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:19:46,217][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:19:46,714][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:19:47,210][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:19:47,708][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:19:48,205][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:19:48,702][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:19:49,199][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:19:49,697][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:19:50,194][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:19:50,693][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:19:51,192][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:19:51,689][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:19:52,187][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:19:52,684][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:19:53,181][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:19:53,679][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:19:54,176][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20010 tokens. [2026-03-25 16:19:55,822][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.03%, Current % of VRAM taken: 60.39%, Block Peak % of device VRAM: 62.05%, ΔTime: 00:01:10 [2026-03-25 16:19:56,544][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:19:56,546][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:19:56,548][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:19:57,346][__main__][INFO] - Iteration 27 took 1m 28s (15.30% Gen, 83.80% Train). Generation: 13s, Training: 1m 14s. Estimated remaining time: 73h 15m 19s. Estimated total time: 74h 0m 3s. Time estimates for 10 more iterations: 14m 48s, 100 more iterations: 2h 28m 0s, 500 more iterations: 12h 20m 0s. [2026-03-25 16:19:57,349][__main__][INFO] - Starting iteration 27. [2026-03-25 16:19:59,022][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:19:59,023][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:20:13,109][__main__][INFO] - Number of regex retries in iteration 27: 0 [2026-03-25 16:20:13,110][__main__][INFO] - agents played in iteration 27 are Bob, Alice [2026-03-25 16:20:15,652][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:20:16,717][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:20:18,330][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:20:20,080][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:20:20,577][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:20:21,080][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:20:21,579][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:20:22,077][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:20:22,688][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:20:23,185][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:20:23,682][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:20:24,181][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:20:24,679][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:20:25,177][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:20:25,675][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:20:26,173][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:20:26,669][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:20:27,167][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:20:27,678][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:20:28,176][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:20:28,677][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:20:29,177][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:20:29,676][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:20:30,175][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:20:30,675][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:20:31,176][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:20:31,674][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:20:32,172][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:20:33,289][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:20:33,787][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:20:34,284][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:20:34,785][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:20:35,282][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:20:35,783][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:20:36,283][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:20:36,779][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:20:37,278][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:20:37,776][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:20:38,275][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:20:38,771][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:20:39,267][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:20:39,768][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:20:40,275][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:20:40,776][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:20:41,277][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:20:42,017][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:20:42,519][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:20:43,598][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:20:44,101][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:20:44,611][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:20:45,109][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:20:45,607][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:20:46,106][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:20:46,604][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:20:47,101][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:20:47,599][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:20:48,098][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:20:48,597][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:20:49,096][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:20:49,595][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:20:50,094][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:20:50,595][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:20:51,094][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:20:51,596][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:20:52,095][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:20:52,594][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:20:53,096][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:20:53,597][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:20:54,095][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:20:54,603][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:20:55,103][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:20:55,603][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:20:56,104][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:20:56,602][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:20:57,097][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:20:57,596][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:20:58,093][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:20:58,590][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:20:59,087][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:20:59,582][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:21:00,078][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:21:00,577][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:21:01,078][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:21:01,575][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:21:02,077][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:21:02,575][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:21:03,075][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:21:03,574][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:21:04,070][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:21:04,572][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:21:05,072][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:21:05,574][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:21:06,073][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:21:06,572][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:21:07,071][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:21:07,576][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:21:08,074][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:21:08,576][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:21:09,076][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:21:09,573][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:21:10,073][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:21:10,575][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:21:11,076][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:21:11,573][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:21:12,070][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:21:12,574][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:21:13,076][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:21:13,577][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:21:14,079][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:21:14,580][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:21:15,081][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:21:15,582][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:21:16,082][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:21:16,583][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:21:17,080][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:21:17,579][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:21:18,078][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:21:18,576][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:21:19,076][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:21:19,575][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:21:20,073][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:21:20,575][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:21:21,075][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:21:21,574][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:21:22,073][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:21:22,571][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:21:23,070][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:21:23,566][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:21:24,063][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:21:24,562][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20205 tokens. [2026-03-25 16:21:25,209][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.14%, Current % of VRAM taken: 60.50%, Block Peak % of device VRAM: 62.26%, ΔTime: 00:01:08 [2026-03-25 16:21:25,932][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:21:25,935][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:21:25,936][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:21:26,721][__main__][INFO] - Iteration 28 took 1m 27s (16.06% Gen, 83.04% Train). Generation: 14s, Training: 1m 12s. Estimated remaining time: 72h 18m 44s. Estimated total time: 73h 4m 57s. Time estimates for 10 more iterations: 14m 36s, 100 more iterations: 2h 26m 9s, 500 more iterations: 12h 10m 49s. [2026-03-25 16:21:26,723][__main__][INFO] - Starting iteration 28. [2026-03-25 16:21:27,122][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:21:27,123][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:21:27,859][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:21:32,465][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:21:39,061][__main__][INFO] - Number of regex retries in iteration 28: 2 [2026-03-25 16:21:39,061][__main__][INFO] - agents played in iteration 28 are Bob, Alice [2026-03-25 16:21:39,918][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:21:40,522][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:21:40,976][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:21:41,481][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:21:41,978][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:21:42,479][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:21:42,978][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:21:43,474][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:21:43,971][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:21:44,468][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:21:45,152][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:21:46,040][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:21:46,848][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:21:47,629][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:21:48,133][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:21:48,632][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:21:49,384][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:21:49,882][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:21:50,382][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:21:50,881][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:21:51,382][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:21:51,883][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:21:52,380][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:21:52,879][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:21:53,380][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:21:53,882][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:21:54,380][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:21:54,878][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:21:55,376][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:21:55,874][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:21:56,374][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:21:56,872][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:21:57,370][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:21:57,868][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:21:58,370][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:21:58,949][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:21:59,450][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:21:59,950][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:22:00,450][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:22:00,951][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:22:01,453][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:22:01,954][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:22:02,452][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:22:02,950][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:22:03,454][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:22:03,953][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:22:04,450][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:22:04,949][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:22:05,449][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:22:05,946][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:22:06,445][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:22:06,944][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:22:07,444][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:22:07,944][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:22:08,445][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:22:08,942][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:22:09,441][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:22:09,939][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:22:10,437][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:22:10,938][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:22:11,436][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:22:11,936][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:22:12,434][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:22:12,934][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:22:13,434][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:22:13,933][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:22:14,430][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:22:14,927][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:22:15,423][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:22:15,921][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:22:16,418][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:22:16,914][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:22:17,411][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:22:17,907][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:22:18,407][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:22:18,908][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:22:19,406][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:22:19,905][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:22:20,405][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:22:20,904][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:22:21,404][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:22:21,904][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:22:22,465][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:22:22,964][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:22:23,465][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:22:23,965][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:22:24,464][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:22:24,963][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:22:25,463][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:22:25,964][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:22:26,462][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:22:26,960][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:22:27,458][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:22:27,956][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:22:28,455][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:22:28,954][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:22:29,453][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:22:29,953][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:22:30,454][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:22:30,955][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:22:31,455][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:22:31,956][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:22:32,456][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:22:32,957][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:22:33,456][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:22:33,968][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:22:34,465][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:22:34,966][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:22:35,464][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:22:35,962][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:22:36,461][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:22:36,962][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:22:37,461][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:22:37,959][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:22:38,457][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:22:38,956][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:22:39,455][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:22:39,955][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:22:40,456][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:22:40,954][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:22:41,453][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:22:41,953][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:22:42,451][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:22:42,948][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:22:43,447][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:22:43,945][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:22:44,443][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:22:44,941][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:22:45,439][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:22:45,938][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20307 tokens. [2026-03-25 16:22:47,003][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.12%, Current % of VRAM taken: 60.48%, Block Peak % of device VRAM: 62.13%, ΔTime: 00:01:06 [2026-03-25 16:22:47,724][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:22:47,727][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:22:47,728][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:22:48,411][__main__][INFO] - Iteration 29 took 1m 21s (14.69% Gen, 84.47% Train). Generation: 11s, Training: 1m 8s. Estimated remaining time: 66h 56m 53s. Estimated total time: 67h 44m 28s. Time estimates for 10 more iterations: 13m 32s, 100 more iterations: 2h 15m 28s, 500 more iterations: 11h 17m 24s. [2026-03-25 16:22:48,413][__main__][INFO] - Starting iteration 29. [2026-03-25 16:22:49,470][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:22:49,470][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:22:51,328][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:22:52,563][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:23:03,888][__main__][INFO] - Number of regex retries in iteration 29: 2 [2026-03-25 16:23:03,889][__main__][INFO] - agents played in iteration 29 are Bob, Alice [2026-03-25 16:23:05,957][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:23:07,024][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:23:08,633][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:23:10,384][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:23:10,885][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:23:11,393][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:23:11,894][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:23:12,395][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:23:12,897][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:23:13,400][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:23:13,901][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:23:14,399][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:23:14,901][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:23:15,403][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:23:15,904][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:23:16,402][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:23:16,904][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:23:17,405][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:23:17,903][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:23:18,403][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:23:18,901][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:23:19,400][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:23:19,898][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:23:20,398][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:23:20,896][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:23:21,395][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:23:21,896][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:23:22,398][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:23:22,899][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:23:23,400][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:23:23,901][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:23:24,409][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:23:24,911][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:23:25,411][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:23:25,911][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:23:26,410][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:23:26,909][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:23:27,408][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:23:27,907][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:23:28,405][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:23:28,904][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:23:29,401][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:23:29,900][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:23:30,401][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:23:30,899][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:23:31,402][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:23:31,899][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:23:32,400][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:23:32,900][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:23:33,400][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:23:33,898][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:23:34,398][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:23:34,897][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:23:35,397][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:23:35,895][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:23:36,394][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:23:36,893][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:23:37,391][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:23:37,890][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:23:38,392][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:23:38,893][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:23:39,393][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:23:39,894][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:23:40,392][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:23:40,893][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:23:41,391][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:23:41,890][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:23:42,393][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:23:42,893][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:23:43,395][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:23:43,894][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:23:44,392][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:23:44,894][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:23:45,394][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:23:45,895][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:23:46,395][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:23:46,896][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:23:47,397][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:23:47,897][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:23:48,397][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:23:48,899][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:23:49,399][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:23:49,897][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:23:50,396][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:23:50,895][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:23:51,393][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:23:51,890][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:23:52,388][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:23:52,885][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:23:53,383][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:23:53,884][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:23:54,385][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:23:54,885][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:23:55,386][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:23:55,887][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:23:56,388][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:23:56,888][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:23:57,390][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:23:57,889][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:23:58,389][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:23:58,886][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:23:59,384][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:23:59,882][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:24:00,380][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:24:00,880][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:24:01,379][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:24:01,878][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:24:02,379][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:24:02,878][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:24:03,375][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:24:03,873][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:24:04,373][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:24:04,872][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:24:05,373][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:24:05,871][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:24:06,371][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:24:06,872][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:24:07,372][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:24:07,874][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:24:08,374][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:24:08,874][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:24:09,374][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:24:09,871][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:24:10,371][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:24:10,868][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:24:11,366][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:24:11,865][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:24:12,363][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:24:12,861][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:24:13,361][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20504 tokens. [2026-03-25 16:24:15,005][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.12%, Current % of VRAM taken: 60.48%, Block Peak % of device VRAM: 62.15%, ΔTime: 00:01:07 [2026-03-25 16:24:15,732][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:24:15,734][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:24:15,735][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:24:16,449][__main__][INFO] - Iteration 30 took 1m 26s (16.58% Gen, 82.60% Train). Generation: 14s, Training: 1m 11s. Estimated remaining time: 71h 39m 57s. Estimated total time: 72h 29m 0s. Time estimates for 10 more iterations: 14m 29s, 100 more iterations: 2h 24m 58s, 500 more iterations: 12h 4m 50s. [2026-03-25 16:24:16,451][__main__][INFO] - Starting iteration 30. [2026-03-25 16:24:17,486][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:24:17,487][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:24:30,438][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:24:31,916][__main__][INFO] - Number of regex retries in iteration 30: 1 [2026-03-25 16:24:31,916][__main__][INFO] - agents played in iteration 30 are Bob, Alice [2026-03-25 16:24:33,957][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:24:35,024][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:24:36,637][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:24:37,767][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:24:38,381][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:24:39,383][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:24:39,882][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:24:40,381][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:24:40,879][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:24:42,001][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:24:42,499][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:24:42,998][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:24:43,497][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:24:43,995][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:24:44,494][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:24:44,993][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:24:45,492][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:24:45,990][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:24:46,488][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:24:46,986][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:24:47,485][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:24:47,983][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:24:48,481][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:24:48,980][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:24:49,481][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:24:49,979][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:24:50,476][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:24:50,972][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:24:51,468][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:24:51,964][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:24:52,460][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:24:52,956][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:24:53,453][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:24:53,950][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:24:54,448][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:24:54,948][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:24:55,446][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:24:55,944][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:24:56,444][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:24:56,944][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:24:57,443][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:24:57,955][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:24:58,455][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:24:58,954][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:24:59,453][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:24:59,953][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:25:00,452][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:25:00,950][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:25:01,448][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:25:02,034][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:25:02,530][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:25:03,028][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:25:03,525][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:25:04,023][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:25:04,521][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:25:05,020][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:25:05,519][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:25:06,017][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:25:06,515][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:25:07,013][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:25:07,514][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:25:08,013][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:25:08,512][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:25:09,011][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:25:09,511][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:25:10,008][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:25:10,506][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:25:11,004][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:25:11,504][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:25:12,003][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:25:12,503][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:25:13,001][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:25:13,501][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:25:13,999][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:25:14,498][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:25:14,998][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:25:15,498][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:25:15,996][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:25:16,494][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:25:16,991][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:25:17,489][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:25:17,987][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:25:18,487][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:25:18,984][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:25:19,483][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:25:19,981][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:25:20,482][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:25:20,982][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:25:21,480][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:25:21,979][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:25:22,477][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:25:22,975][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:25:23,471][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:25:23,969][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:25:24,466][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:25:24,962][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:25:25,459][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:25:25,955][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:25:26,456][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:25:26,956][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:25:27,455][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:25:27,955][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:25:28,454][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:25:28,955][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:25:29,466][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:25:29,966][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:25:30,463][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:25:30,964][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:25:31,462][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:25:31,961][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:25:32,460][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:25:32,958][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:25:33,459][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:25:33,958][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:25:34,456][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:25:34,955][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:25:35,453][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:25:35,951][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:25:36,448][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:25:36,947][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:25:37,445][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:25:37,942][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:25:38,440][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:25:38,938][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:25:39,435][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:25:39,935][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:25:40,434][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:25:40,933][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:25:41,432][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:25:41,930][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20512 tokens. [2026-03-25 16:25:42,987][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.06%, Current % of VRAM taken: 60.42%, Block Peak % of device VRAM: 61.98%, ΔTime: 00:01:07 [2026-03-25 16:25:43,712][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:25:43,714][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:25:43,716][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:25:44,448][__main__][INFO] - Iteration 31 took 1m 26s (16.59% Gen, 82.56% Train). Generation: 14s, Training: 1m 11s. Estimated remaining time: 71h 37m 37s. Estimated total time: 72h 28m 9s. Time estimates for 10 more iterations: 14m 29s, 100 more iterations: 2h 24m 56s, 500 more iterations: 12h 4m 41s. [2026-03-25 16:25:44,451][__main__][INFO] - Starting iteration 31. [2026-03-25 16:25:45,483][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:25:45,483][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:25:46,506][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:25:58,806][__main__][INFO] - Number of regex retries in iteration 31: 1 [2026-03-25 16:25:58,806][__main__][INFO] - agents played in iteration 31 are Bob, Alice [2026-03-25 16:26:01,064][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:26:02,133][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:26:03,743][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:26:04,871][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:26:05,504][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:26:06,004][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:26:06,504][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:26:07,232][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:26:07,733][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:26:08,234][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:26:08,731][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:26:09,228][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:26:09,726][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:26:10,226][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:26:10,724][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:26:11,223][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:26:11,722][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:26:12,222][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:26:12,720][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:26:13,219][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:26:13,717][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:26:14,218][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:26:14,717][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:26:15,215][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:26:15,714][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:26:16,213][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:26:16,711][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:26:17,209][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:26:17,706][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:26:18,203][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:26:18,701][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:26:19,201][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:26:19,698][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:26:20,198][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:26:20,696][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:26:21,198][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:26:21,698][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:26:22,197][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:26:22,699][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:26:23,197][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:26:23,696][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:26:24,195][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:26:24,694][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:26:25,198][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:26:25,700][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:26:26,199][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:26:26,698][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:26:27,197][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:26:27,697][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:26:28,196][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:26:28,694][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:26:29,192][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:26:29,690][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:26:30,189][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:26:30,686][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:26:31,183][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:26:31,687][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:26:32,186][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:26:32,685][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:26:33,184][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:26:33,685][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:26:34,182][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:26:34,682][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:26:35,181][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:26:35,681][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:26:36,181][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:26:36,681][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:26:37,182][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:26:37,683][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:26:38,184][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:26:38,684][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:26:39,183][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:26:39,683][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:26:40,183][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:26:40,680][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:26:41,178][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:26:41,677][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:26:42,175][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:26:42,674][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:26:43,170][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:26:43,667][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:26:44,165][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:26:44,662][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:26:45,163][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:26:45,660][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:26:46,158][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:26:46,658][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:26:47,155][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:26:47,656][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:26:48,153][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:26:48,651][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:26:49,148][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:26:49,645][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:26:50,142][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:26:50,641][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:26:51,139][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:26:51,637][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:26:52,134][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:26:52,631][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:26:53,128][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:26:53,625][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:26:54,123][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:26:54,621][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:26:55,120][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:26:55,620][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:26:56,118][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:26:56,616][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:26:57,117][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:26:57,616][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:26:58,116][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:26:58,614][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:26:59,113][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:26:59,612][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:27:00,111][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:27:00,607][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:27:01,103][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:27:01,600][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:27:02,098][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:27:02,596][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:27:03,094][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:27:03,592][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:27:04,089][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:27:04,587][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:27:05,085][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:27:05,586][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:27:06,083][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:27:06,582][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:27:07,082][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:27:07,583][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:27:08,084][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20457 tokens. [2026-03-25 16:27:09,239][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.23%, ΔTime: 00:01:07 [2026-03-25 16:27:10,004][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:27:10,006][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:27:10,007][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:27:10,643][__main__][INFO] - Iteration 32 took 1m 25s (15.64% Gen, 83.61% Train). Generation: 13s, Training: 1m 11s. Estimated remaining time: 70h 6m 6s. Estimated total time: 70h 58m 4s. Time estimates for 10 more iterations: 14m 11s, 100 more iterations: 2h 21m 56s, 500 more iterations: 11h 49m 40s. [2026-03-25 16:27:10,645][__main__][INFO] - Starting iteration 32. [2026-03-25 16:27:11,709][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:27:11,710][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:27:24,358][__main__][INFO] - Number of regex retries in iteration 32: 0 [2026-03-25 16:27:24,360][__main__][INFO] - agents played in iteration 32 are Bob, Alice [2026-03-25 16:27:26,459][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:27:27,529][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:27:29,141][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:27:30,265][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:27:30,765][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:27:31,263][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:27:31,890][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:27:32,391][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:27:32,888][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:27:33,387][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:27:33,885][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:27:34,382][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:27:34,881][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:27:35,379][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:27:35,876][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:27:36,377][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:27:36,877][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:27:37,376][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:27:37,876][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:27:38,721][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:27:39,740][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:27:40,240][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:27:40,739][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:27:41,239][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:27:41,738][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:27:42,239][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:27:42,739][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:27:43,239][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:27:43,739][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:27:44,252][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:27:44,754][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:27:45,254][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:27:45,755][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:27:46,255][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:27:46,750][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:27:47,248][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:27:47,746][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:27:48,245][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:27:48,744][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:27:49,242][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:27:49,741][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:27:50,239][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:27:50,740][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:27:51,239][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:27:51,740][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:27:52,241][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:27:52,741][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:27:53,241][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:27:53,740][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:27:54,240][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:27:54,738][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:27:55,237][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:27:55,736][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:27:56,235][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:27:56,732][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:27:57,230][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:27:57,728][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:27:58,225][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:27:58,723][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:27:59,223][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:27:59,723][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:28:00,224][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:28:00,725][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:28:01,224][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:28:01,721][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:28:02,221][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:28:02,719][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:28:03,218][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:28:03,717][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:28:04,215][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:28:04,715][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:28:05,214][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:28:05,715][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:28:06,212][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:28:06,710][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:28:07,209][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:28:07,706][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:28:08,204][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:28:08,702][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:28:09,200][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:28:09,699][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:28:10,197][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:28:10,695][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:28:11,196][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:28:11,697][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:28:12,197][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:28:12,696][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:28:13,198][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:28:13,696][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:28:14,198][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:28:14,697][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:28:15,196][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:28:15,697][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:28:16,195][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:28:16,694][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:28:17,196][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:28:17,696][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:28:18,195][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:28:18,694][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:28:19,191][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:28:19,691][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:28:20,188][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:28:20,686][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:28:21,185][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:28:21,685][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:28:22,183][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:28:22,684][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:28:23,184][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:28:23,684][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:28:24,183][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:28:24,683][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:28:25,183][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:28:25,683][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:28:26,182][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:28:26,679][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:28:27,178][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:28:27,677][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:28:28,174][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:28:28,672][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:28:29,170][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:28:29,675][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:28:30,172][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:28:30,671][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:28:31,172][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:28:31,672][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:28:32,174][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:28:32,672][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:28:33,172][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:28:33,670][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:28:34,169][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20573 tokens. [2026-03-25 16:28:35,481][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.12%, Current % of VRAM taken: 60.47%, Block Peak % of device VRAM: 62.03%, ΔTime: 00:01:07 [2026-03-25 16:28:36,203][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:28:36,205][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:28:36,206][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:28:36,892][__main__][INFO] - Iteration 33 took 1m 25s (14.85% Gen, 84.34% Train). Generation: 12s, Training: 1m 11s. Estimated remaining time: 70h 5m 49s. Estimated total time: 70h 59m 12s. Time estimates for 10 more iterations: 14m 11s, 100 more iterations: 2h 21m 58s, 500 more iterations: 11h 49m 52s. [2026-03-25 16:28:36,895][__main__][INFO] - Starting iteration 33. [2026-03-25 16:28:37,949][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:28:37,950][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:28:38,952][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:28:50,277][__main__][INFO] - Number of regex retries in iteration 33: 1 [2026-03-25 16:28:50,278][__main__][INFO] - agents played in iteration 33 are Bob, Alice [2026-03-25 16:28:52,694][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:28:53,759][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:28:55,373][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:28:56,506][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:28:57,251][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:28:57,753][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:28:58,859][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:28:59,359][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:28:59,859][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:29:00,359][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:29:00,858][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:29:01,357][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:29:01,856][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:29:02,354][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:29:02,851][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:29:03,348][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:29:04,183][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:29:04,682][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:29:05,185][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:29:05,685][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:29:06,800][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:29:07,710][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:29:08,211][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:29:08,713][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:29:09,214][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:29:09,719][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:29:10,220][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:29:10,718][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:29:11,218][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:29:11,720][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:29:12,221][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:29:12,722][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:29:13,220][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:29:13,723][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:29:14,221][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:29:14,721][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:29:15,220][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:29:15,720][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:29:16,220][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:29:16,720][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:29:17,220][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:29:17,720][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:29:18,220][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:29:18,720][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:29:19,219][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:29:19,719][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:29:20,222][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:29:20,721][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:29:21,221][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:29:21,720][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:29:22,220][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:29:22,718][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:29:23,220][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:29:23,717][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:29:24,219][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:29:24,720][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:29:25,218][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:29:25,717][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:29:26,216][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:29:26,716][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:29:27,216][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:29:27,715][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:29:28,215][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:29:28,716][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:29:29,216][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:29:29,717][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:29:30,218][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:29:30,718][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:29:31,219][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:29:31,720][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:29:32,221][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:29:32,721][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:29:33,222][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:29:33,722][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:29:34,220][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:29:34,719][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:29:35,219][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:29:35,716][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:29:36,214][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:29:36,713][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:29:37,212][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:29:37,710][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:29:38,213][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:29:38,714][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:29:39,217][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:29:39,721][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:29:40,223][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:29:40,724][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:29:41,225][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:29:41,729][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:29:42,231][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:29:42,729][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:29:43,229][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:29:43,729][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:29:44,231][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:29:44,733][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:29:45,233][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:29:45,734][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:29:46,231][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:29:46,729][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:29:47,227][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:29:47,727][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:29:48,226][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:29:48,726][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:29:49,224][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:29:49,723][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:29:50,220][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:29:50,719][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:29:51,218][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:29:51,716][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:29:52,218][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:29:52,716][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:29:53,215][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:29:53,713][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:29:54,213][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:29:54,711][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:29:55,210][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:29:55,711][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:29:56,209][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:29:56,708][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:29:57,206][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:29:57,704][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:29:58,203][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:29:58,705][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:29:59,205][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:29:59,703][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:30:00,204][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:30:00,702][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:30:01,202][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:30:01,703][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20767 tokens. [2026-03-25 16:30:03,475][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.26%, ΔTime: 00:01:09 [2026-03-25 16:30:04,191][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:30:04,193][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:30:04,195][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:30:04,881][__main__][INFO] - Iteration 34 took 1m 26s (14.18% Gen, 85.03% Train). Generation: 12s, Training: 1m 13s. Estimated remaining time: 71h 31m 46s. Estimated total time: 72h 26m 38s. Time estimates for 10 more iterations: 14m 29s, 100 more iterations: 2h 24m 53s, 500 more iterations: 12h 4m 26s. [2026-03-25 16:30:04,883][__main__][INFO] - Starting iteration 34. [2026-03-25 16:30:05,948][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:30:05,948][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:30:07,976][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 5 books, 5 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:30:19,184][__main__][INFO] - Number of regex retries in iteration 34: 1 [2026-03-25 16:30:19,185][__main__][INFO] - agents played in iteration 34 are Bob, Alice [2026-03-25 16:30:21,562][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:30:22,629][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:30:24,246][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:30:25,367][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:30:26,145][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:30:26,644][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:30:27,142][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:30:27,864][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:30:28,361][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:30:28,859][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:30:29,606][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:30:30,105][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:30:31,219][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:30:31,720][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:30:32,220][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:30:32,718][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:30:33,219][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:30:33,720][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:30:34,218][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:30:34,719][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:30:35,219][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:30:35,728][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:30:36,441][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:30:36,939][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:30:37,439][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:30:37,939][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:30:38,435][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:30:38,933][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:30:39,430][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:30:39,926][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:30:40,422][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:30:40,919][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:30:41,418][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:30:41,917][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:30:42,415][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:30:42,913][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:30:43,412][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:30:43,910][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:30:44,408][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:30:44,906][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:30:45,405][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:30:45,902][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:30:46,400][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:30:46,899][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:30:47,397][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:30:47,896][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:30:48,394][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:30:48,894][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:30:49,395][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:30:49,894][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:30:50,546][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:30:51,386][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:30:51,886][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:30:52,993][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:30:53,494][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:30:53,996][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:30:54,751][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:30:55,251][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:30:55,749][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:30:56,248][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:30:56,748][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:30:57,248][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:30:57,748][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:30:58,251][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:30:58,752][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:30:59,254][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:30:59,750][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:31:00,246][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:31:00,745][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:31:01,243][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:31:01,741][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:31:02,239][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:31:02,738][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:31:03,237][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:31:03,736][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:31:04,236][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:31:04,737][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:31:05,237][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:31:05,737][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:31:06,234][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:31:06,735][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:31:07,233][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:31:07,733][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:31:08,235][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:31:08,733][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:31:09,234][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:31:09,734][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:31:10,235][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:31:10,733][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:31:11,231][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:31:11,727][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:31:12,224][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:31:12,719][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:31:13,215][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:31:13,713][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:31:14,209][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:31:14,705][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:31:15,202][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:31:15,700][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:31:16,197][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:31:16,697][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:31:17,195][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:31:17,694][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:31:18,193][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:31:18,691][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:31:19,188][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:31:19,685][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:31:20,183][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:31:20,681][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:31:21,179][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:31:21,678][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:31:22,179][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:31:22,680][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:31:23,177][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:31:23,679][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:31:24,365][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:31:24,865][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:31:25,367][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:31:25,868][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:31:26,368][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:31:26,869][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:31:27,368][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:31:27,867][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:31:28,365][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:31:28,863][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:31:29,364][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:31:29,864][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:31:30,365][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:31:30,863][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:31:31,364][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20336 tokens. [2026-03-25 16:31:32,343][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.26%, ΔTime: 00:01:09 [2026-03-25 16:31:33,117][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:31:33,119][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:31:33,121][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:31:33,750][__main__][INFO] - Iteration 35 took 1m 27s (15.08% Gen, 84.21% Train). Generation: 13s, Training: 1m 13s. Estimated remaining time: 72h 13m 50s. Estimated total time: 73h 10m 10s. Time estimates for 10 more iterations: 14m 38s, 100 more iterations: 2h 26m 20s, 500 more iterations: 12h 11m 41s. [2026-03-25 16:31:33,752][__main__][INFO] - Starting iteration 35. [2026-03-25 16:31:34,815][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:31:34,816][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:31:48,059][__main__][INFO] - Number of regex retries in iteration 35: 0 [2026-03-25 16:31:48,060][__main__][INFO] - agents played in iteration 35 are Bob, Alice [2026-03-25 16:31:50,431][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:31:51,498][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:31:53,110][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:31:53,632][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:31:54,130][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:31:54,633][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:31:55,132][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:31:55,631][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:31:56,131][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:31:56,633][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:31:57,132][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:31:57,633][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:31:58,134][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:31:58,634][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:31:59,134][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:31:59,635][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:32:00,136][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:32:00,635][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:32:01,137][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:32:01,637][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:32:02,735][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:32:03,244][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:32:03,747][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:32:04,248][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:32:04,748][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:32:05,250][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:32:05,751][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:32:06,253][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:32:06,755][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:32:07,256][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:32:07,756][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:32:08,256][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:32:08,754][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:32:09,256][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:32:09,755][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:32:10,256][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:32:10,755][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:32:11,255][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:32:11,755][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:32:12,253][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:32:12,751][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:32:13,254][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:32:13,754][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:32:14,255][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:32:14,755][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:32:15,257][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:32:15,756][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:32:16,256][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:32:16,757][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:32:17,257][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:32:17,757][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:32:18,258][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:32:18,758][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:32:19,259][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:32:19,759][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:32:20,260][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:32:20,760][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:32:21,257][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:32:21,758][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:32:22,256][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:32:22,757][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:32:23,258][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:32:23,758][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:32:24,260][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:32:24,758][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:32:25,299][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:32:25,800][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:32:26,301][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:32:26,802][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:32:27,303][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:32:27,801][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:32:28,302][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:32:28,803][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:32:29,306][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:32:29,807][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:32:30,305][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:32:30,807][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:32:31,308][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:32:31,806][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:32:32,308][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:32:32,808][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:32:33,308][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:32:33,809][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:32:34,309][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:32:34,814][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:32:35,316][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:32:35,817][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:32:36,319][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:32:36,820][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:32:37,323][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:32:37,823][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:32:38,324][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:32:38,826][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:32:39,327][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:32:39,827][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:32:40,326][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:32:40,823][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:32:41,325][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:32:41,823][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:32:42,323][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:32:42,822][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:32:43,322][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:32:43,821][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:32:44,320][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:32:44,820][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:32:45,320][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:32:45,822][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:32:46,323][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:32:46,823][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:32:47,323][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:32:47,824][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:32:48,325][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:32:48,825][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:32:49,327][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:32:49,827][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:32:50,328][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:32:50,828][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:32:51,329][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:32:51,827][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:32:52,328][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:32:52,829][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:32:53,327][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:32:53,826][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:32:54,324][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:32:54,823][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:32:55,323][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:32:55,821][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:32:56,319][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:32:56,818][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:32:57,319][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20782 tokens. [2026-03-25 16:32:58,617][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.16%, Current % of VRAM taken: 60.51%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:07 [2026-03-25 16:32:59,338][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:32:59,340][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:32:59,342][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:33:00,017][__main__][INFO] - Iteration 36 took 1m 25s (15.54% Gen, 83.66% Train). Generation: 13s, Training: 1m 11s. Estimated remaining time: 70h 2m 19s. Estimated total time: 71h 0m 6s. Time estimates for 10 more iterations: 14m 12s, 100 more iterations: 2h 22m 0s, 500 more iterations: 11h 50m 1s. [2026-03-25 16:33:00,019][__main__][INFO] - Starting iteration 36. [2026-03-25 16:33:01,086][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:33:01,087][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:33:14,512][__main__][INFO] - Number of regex retries in iteration 36: 0 [2026-03-25 16:33:14,513][__main__][INFO] - agents played in iteration 36 are Bob, Alice [2026-03-25 16:33:16,707][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:33:17,776][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:33:19,389][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:33:20,531][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:33:21,148][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:33:22,138][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:33:22,637][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:33:23,137][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:33:23,762][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:33:24,260][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:33:24,764][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:33:25,264][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:33:25,763][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:33:26,527][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:33:27,365][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:33:27,865][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:33:28,365][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:33:28,862][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:33:29,363][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:33:29,861][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:33:30,360][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:33:30,859][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:33:31,586][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:33:32,473][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:33:32,969][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:33:33,468][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:33:33,968][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:33:35,070][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:33:35,942][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:33:36,440][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:33:36,941][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:33:37,438][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:33:37,935][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:33:38,437][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:33:38,936][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:33:39,437][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:33:39,937][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:33:40,435][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:33:40,933][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:33:41,433][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:33:41,930][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:33:42,429][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:33:42,927][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:33:43,428][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:33:43,928][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:33:44,428][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:33:44,926][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:33:45,426][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:33:45,923][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:33:46,422][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:33:46,923][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:33:47,423][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:33:47,924][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:33:48,425][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:33:48,925][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:33:49,425][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:33:49,926][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:33:50,427][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:33:50,924][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:33:51,423][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:33:51,921][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:33:52,420][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:33:52,918][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:33:53,416][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:33:53,914][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:33:54,412][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:33:54,909][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:33:55,407][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:33:55,916][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:33:56,415][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:33:56,913][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:33:57,411][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:33:57,909][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:33:58,407][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:33:58,908][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:33:59,405][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:33:59,906][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:34:00,408][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:34:00,909][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:34:01,410][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:34:01,910][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:34:02,411][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:34:02,911][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:34:03,411][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:34:03,911][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:34:04,409][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:34:04,911][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:34:05,411][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:34:05,910][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:34:06,409][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:34:06,910][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:34:07,410][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:34:07,913][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:34:08,412][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:34:08,913][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:34:09,412][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:34:09,910][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:34:10,410][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:34:10,910][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:34:11,412][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:34:11,914][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:34:12,415][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:34:12,915][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:34:13,415][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:34:13,915][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:34:14,416][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:34:14,913][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:34:15,415][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:34:15,913][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:34:16,413][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:34:16,911][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:34:17,409][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:34:17,908][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:34:18,410][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:34:18,910][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:34:19,411][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:34:19,912][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:34:20,411][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:34:20,912][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:34:21,412][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:34:21,914][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:34:22,415][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:34:22,913][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:34:23,411][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:34:23,910][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:34:24,407][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:34:24,903][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:34:25,401][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:34:25,900][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:34:26,399][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20744 tokens. [2026-03-25 16:34:27,467][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.09%, Current % of VRAM taken: 60.44%, Block Peak % of device VRAM: 62.16%, ΔTime: 00:01:09 [2026-03-25 16:34:28,189][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:34:28,405][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:34:28,407][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:34:29,063][__main__][INFO] - Iteration 37 took 1m 27s (15.26% Gen, 83.99% Train). Generation: 13s, Training: 1m 13s. Estimated remaining time: 72h 19m 35s. Estimated total time: 73h 18m 51s. Time estimates for 10 more iterations: 14m 39s, 100 more iterations: 2h 26m 37s, 500 more iterations: 12h 13m 8s. [2026-03-25 16:34:29,065][__main__][INFO] - Starting iteration 37. [2026-03-25 16:34:30,732][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:34:30,733][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:34:43,949][__main__][INFO] - Number of regex retries in iteration 37: 0 [2026-03-25 16:34:43,950][__main__][INFO] - agents played in iteration 37 are Bob, Alice [2026-03-25 16:34:46,424][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:34:47,490][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:34:48,088][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:34:48,579][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:34:49,082][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:34:49,582][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:34:50,123][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:34:50,623][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:34:51,125][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:34:51,625][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:34:52,123][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:34:52,625][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:34:53,123][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:34:53,624][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:34:54,125][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:34:54,624][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:34:55,121][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:34:55,620][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:34:56,120][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:34:56,619][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:34:57,122][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:34:57,623][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:34:58,121][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:34:58,622][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:34:59,124][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:34:59,626][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:35:00,122][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:35:00,619][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:35:01,117][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:35:01,615][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:35:02,113][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:35:02,612][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:35:03,110][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:35:03,607][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:35:04,104][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:35:04,601][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:35:05,102][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:35:05,600][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:35:06,100][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:35:06,600][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:35:07,101][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:35:07,599][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:35:08,101][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:35:09,141][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:35:09,642][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:35:10,141][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:35:10,641][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:35:11,142][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:35:11,642][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:35:12,143][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:35:12,641][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:35:13,139][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:35:13,638][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:35:14,138][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:35:14,636][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:35:15,135][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:35:15,633][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:35:16,131][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:35:16,632][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:35:17,131][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:35:17,633][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:35:18,134][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:35:18,635][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:35:19,136][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:35:19,637][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:35:20,137][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:35:20,638][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:35:21,326][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:35:21,837][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:35:22,339][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:35:22,841][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:35:23,342][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:35:23,843][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:35:24,344][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:35:24,841][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:35:25,340][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:35:25,838][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:35:26,335][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:35:26,836][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:35:27,333][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:35:27,829][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:35:28,328][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:35:28,878][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:35:29,378][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:35:29,876][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:35:30,378][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:35:30,876][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:35:31,377][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:35:31,877][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:35:32,377][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:35:32,873][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:35:33,368][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:35:33,864][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:35:34,360][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:35:34,857][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:35:35,354][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:35:35,850][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:35:36,346][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:35:36,842][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:35:37,341][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:35:37,839][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:35:38,338][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:35:38,837][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:35:39,336][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:35:39,834][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:35:40,334][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:35:40,834][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:35:41,335][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:35:41,836][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:35:42,334][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:35:42,835][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:35:43,336][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:35:43,837][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:35:44,337][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:35:44,837][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:35:45,333][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:35:45,830][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:35:46,328][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:35:46,825][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:35:47,323][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:35:47,820][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:35:48,320][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:35:48,821][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:35:49,321][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:35:49,819][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:35:50,320][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:35:50,820][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:35:51,321][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:35:51,821][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:35:52,323][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20495 tokens. [2026-03-25 16:35:53,700][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.25%, ΔTime: 00:01:06 [2026-03-25 16:35:54,418][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:35:54,421][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:35:54,423][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:35:55,116][__main__][INFO] - Iteration 38 took 1m 24s (15.66% Gen, 83.51% Train). Generation: 13s, Training: 1m 10s. Estimated remaining time: 69h 18m 30s. Estimated total time: 70h 19m 12s. Time estimates for 10 more iterations: 14m 3s, 100 more iterations: 2h 20m 38s, 500 more iterations: 11h 43m 12s. [2026-03-25 16:35:55,118][__main__][INFO] - Starting iteration 38. [2026-03-25 16:35:56,167][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:35:56,167][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:36:09,564][__main__][INFO] - Number of regex retries in iteration 38: 0 [2026-03-25 16:36:09,565][__main__][INFO] - agents played in iteration 38 are Bob, Alice [2026-03-25 16:36:11,785][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:36:12,853][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:36:14,465][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:36:14,987][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:36:15,488][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:36:15,990][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:36:16,493][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:36:16,994][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:36:17,496][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:36:17,998][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:36:18,496][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:36:18,992][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:36:19,489][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:36:19,986][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:36:20,483][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:36:20,980][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:36:21,478][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:36:21,976][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:36:22,479][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:36:22,981][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:36:23,483][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:36:23,984][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:36:24,485][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:36:24,985][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:36:25,486][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:36:25,988][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:36:26,486][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:36:26,984][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:36:27,481][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:36:27,982][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:36:28,481][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:36:28,980][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:36:29,481][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:36:29,980][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:36:30,479][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:36:30,980][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:36:31,481][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:36:31,980][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:36:32,480][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:36:32,981][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:36:33,480][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:36:33,980][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:36:34,481][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:36:34,982][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:36:35,482][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:36:35,983][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:36:36,484][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:36:36,986][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:36:37,488][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:36:37,990][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:36:38,489][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:36:38,988][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:36:39,487][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:36:39,985][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:36:40,485][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:36:40,983][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:36:41,483][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:36:41,981][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:36:42,482][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:36:42,984][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:36:43,484][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:36:43,985][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:36:44,485][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:36:44,985][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:36:45,483][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:36:45,984][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:36:46,486][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:36:46,986][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:36:47,485][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:36:47,986][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:36:48,489][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:36:48,989][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:36:49,492][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:36:49,994][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:36:50,490][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:36:50,986][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:36:51,483][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:36:51,981][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:36:52,478][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:36:52,977][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:36:53,475][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:36:53,973][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:36:54,474][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:36:54,977][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:36:55,480][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:36:55,981][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:36:56,482][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:36:56,984][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:36:57,485][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:36:57,987][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:36:58,484][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:36:58,983][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:36:59,481][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:36:59,978][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:37:00,476][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:37:00,974][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:37:01,472][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:37:01,970][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:37:02,468][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:37:02,966][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:37:03,474][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:37:03,976][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:37:04,476][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:37:04,976][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:37:05,476][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:37:05,977][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:37:06,479][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:37:06,980][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:37:07,482][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:37:07,983][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:37:08,485][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:37:08,984][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:37:09,485][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:37:09,985][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:37:10,482][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:37:10,980][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:37:11,479][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:37:11,978][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:37:12,480][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:37:12,978][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:37:13,475][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:37:13,977][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:37:14,479][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:37:14,980][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:37:15,480][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:37:15,980][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:37:16,479][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:37:16,981][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:37:17,479][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:37:17,980][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20768 tokens. [2026-03-25 16:37:19,143][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.16%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.26%, ΔTime: 00:01:06 [2026-03-25 16:37:19,863][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:37:19,865][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:37:19,867][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:37:20,558][__main__][INFO] - Iteration 39 took 1m 24s (15.88% Gen, 83.30% Train). Generation: 13s, Training: 1m 10s. Estimated remaining time: 69h 17m 27s. Estimated total time: 70h 19m 34s. Time estimates for 10 more iterations: 14m 3s, 100 more iterations: 2h 20m 39s, 500 more iterations: 11h 43m 15s. [2026-03-25 16:37:20,560][__main__][INFO] - Starting iteration 39. [2026-03-25 16:37:21,610][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:37:21,610][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:37:22,628][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:37:34,504][__main__][INFO] - Number of regex retries in iteration 39: 1 [2026-03-25 16:37:34,505][__main__][INFO] - agents played in iteration 39 are Bob, Alice [2026-03-25 16:37:36,357][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:37:37,424][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:37:39,037][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:37:40,165][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:37:40,928][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:37:41,429][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:37:41,931][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:37:42,432][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:37:42,935][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:37:43,437][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:37:43,938][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:37:44,436][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:37:44,935][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:37:45,433][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:37:45,934][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:37:46,435][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:37:46,932][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:37:47,434][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:37:47,932][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:37:48,434][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:37:48,932][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:37:49,432][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:37:49,933][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:37:50,431][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:37:50,933][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:37:51,434][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:37:51,934][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:37:52,433][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:37:52,932][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:37:53,430][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:37:53,931][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:37:54,432][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:37:54,930][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:37:55,429][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:37:55,926][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:37:56,426][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:37:56,926][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:37:57,423][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:37:57,921][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:37:58,419][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:37:58,918][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:37:59,417][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:37:59,919][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:38:00,418][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:38:00,916][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:38:01,413][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:38:01,913][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:38:02,411][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:38:02,911][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:38:03,410][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:38:03,912][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:38:04,424][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:38:04,933][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:38:06,051][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:38:06,554][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:38:07,058][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:38:07,559][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:38:08,061][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:38:08,560][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:38:09,061][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:38:09,561][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:38:10,058][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:38:10,557][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:38:11,056][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:38:11,557][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:38:12,057][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:38:12,557][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:38:13,059][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:38:13,559][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:38:14,059][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:38:14,559][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:38:15,059][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:38:15,559][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:38:16,059][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:38:16,560][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:38:17,059][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:38:17,560][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:38:18,060][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:38:18,560][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:38:19,061][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:38:19,560][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:38:20,058][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:38:20,556][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:38:21,057][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:38:21,554][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:38:22,055][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:38:22,555][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:38:23,051][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:38:23,549][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:38:24,052][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:38:24,549][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:38:25,048][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:38:25,547][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:38:26,045][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:38:26,544][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:38:27,045][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:38:27,542][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:38:28,041][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:38:28,539][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:38:29,039][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:38:29,536][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:38:30,034][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:38:30,532][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:38:31,030][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:38:31,528][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:38:32,027][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:38:32,526][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:38:33,027][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:38:33,524][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:38:34,022][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:38:34,520][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:38:35,019][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:38:35,517][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:38:36,016][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:38:36,518][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:38:37,019][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:38:37,521][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:38:38,025][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:38:38,526][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:38:39,027][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:38:39,529][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:38:40,030][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:38:40,530][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:38:41,030][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:38:41,530][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:38:42,031][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:38:42,532][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:38:43,033][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:38:43,532][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:38:44,033][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20744 tokens. [2026-03-25 16:38:45,386][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:07 [2026-03-25 16:38:46,111][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:38:46,114][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:38:46,115][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:38:46,807][__main__][INFO] - Iteration 40 took 1m 25s (15.13% Gen, 84.05% Train). Generation: 12s, Training: 1m 11s. Estimated remaining time: 69h 56m 19s. Estimated total time: 70h 59m 52s. Time estimates for 10 more iterations: 14m 11s, 100 more iterations: 2h 21m 59s, 500 more iterations: 11h 49m 58s. [2026-03-25 16:38:46,809][__main__][INFO] - Starting iteration 40. [2026-03-25 16:38:47,856][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:38:47,857][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:39:00,658][__main__][INFO] - Number of regex retries in iteration 40: 0 [2026-03-25 16:39:00,659][__main__][INFO] - agents played in iteration 40 are Bob, Alice [2026-03-25 16:39:02,597][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:39:03,664][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:39:05,279][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:39:06,411][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:39:07,157][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:39:07,657][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:39:08,762][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:39:09,649][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:39:10,149][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:39:10,647][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:39:11,527][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:39:12,394][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:39:12,896][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:39:13,397][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:39:13,898][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:39:14,864][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:39:15,365][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:39:15,867][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:39:16,367][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:39:16,868][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:39:17,368][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:39:17,870][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:39:18,373][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:39:18,872][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:39:19,371][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:39:19,878][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:39:20,378][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:39:20,876][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:39:21,377][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:39:21,876][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:39:22,374][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:39:22,875][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:39:23,375][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:39:23,874][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:39:24,372][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:39:24,874][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:39:25,373][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:39:25,873][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:39:26,372][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:39:26,870][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:39:27,369][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:39:27,867][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:39:28,369][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:39:28,869][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:39:29,370][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:39:29,871][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:39:30,371][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:39:30,872][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:39:31,369][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:39:31,866][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:39:32,367][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:39:32,877][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:39:33,378][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:39:33,880][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:39:34,381][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:39:34,881][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:39:35,379][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:39:35,878][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:39:36,376][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:39:36,874][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:39:37,372][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:39:37,873][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:39:38,374][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:39:38,876][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:39:39,377][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:39:39,875][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:39:40,375][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:39:40,877][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:39:41,378][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:39:41,877][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:39:42,379][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:39:42,878][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:39:43,379][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:39:43,877][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:39:44,379][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:39:44,879][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:39:45,382][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:39:45,882][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:39:46,384][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:39:46,884][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:39:47,384][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:39:47,882][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:39:48,383][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:39:48,882][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:39:49,384][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:39:49,883][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:39:50,382][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:39:50,880][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:39:51,379][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:39:51,879][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:39:52,377][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:39:52,876][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:39:53,376][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:39:53,874][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:39:54,372][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:39:54,872][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:39:55,373][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:39:55,871][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:39:56,370][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:39:56,872][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:39:57,371][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:39:57,868][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:39:58,366][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:39:58,866][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:39:59,365][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:39:59,863][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:40:00,361][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:40:00,859][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:40:01,361][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:40:01,859][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:40:02,357][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:40:02,858][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:40:03,357][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:40:03,855][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:40:04,354][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:40:04,854][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:40:05,354][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:40:05,853][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:40:06,355][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:40:06,853][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:40:07,351][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:40:07,849][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:40:08,350][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:40:08,849][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:40:09,348][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:40:09,848][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:40:10,348][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:40:10,846][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:40:11,347][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:40:11,847][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20871 tokens. [2026-03-25 16:40:13,376][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.12%, Current % of VRAM taken: 60.48%, Block Peak % of device VRAM: 62.12%, ΔTime: 00:01:09 [2026-03-25 16:40:14,111][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:40:14,116][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:40:14,118][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:40:14,813][__main__][INFO] - Iteration 41 took 1m 26s (14.72% Gen, 84.48% Train). Generation: 12s, Training: 1m 13s. Estimated remaining time: 71h 22m 50s. Estimated total time: 72h 27m 51s. Time estimates for 10 more iterations: 14m 29s, 100 more iterations: 2h 24m 55s, 500 more iterations: 12h 4m 38s. [2026-03-25 16:40:14,815][__main__][INFO] - Starting iteration 41. [2026-03-25 16:40:15,848][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:40:15,849][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:40:29,242][__main__][INFO] - Number of regex retries in iteration 41: 0 [2026-03-25 16:40:29,243][__main__][INFO] - agents played in iteration 41 are Bob, Alice [2026-03-25 16:40:31,443][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:40:32,512][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:40:34,126][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:40:35,873][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:40:36,372][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:40:36,874][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:40:37,755][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:40:38,254][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:40:38,755][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:40:39,256][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:40:39,754][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:40:40,255][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:40:40,756][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:40:41,257][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:40:41,758][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:40:42,258][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:40:42,756][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:40:43,256][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:40:43,857][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:40:44,359][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:40:44,860][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:40:45,360][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:40:45,861][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:40:46,360][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:40:46,860][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:40:47,360][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:40:47,858][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:40:48,358][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:40:48,856][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:40:49,355][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:40:49,856][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:40:50,358][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:40:50,857][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:40:51,355][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:40:51,856][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:40:52,357][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:40:52,856][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:40:53,357][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:40:53,859][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:40:54,359][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:40:54,860][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:40:55,360][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:40:55,857][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:40:56,355][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:40:56,854][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:40:57,353][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:40:57,852][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:40:58,349][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:40:58,848][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:40:59,346][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:40:59,843][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:41:00,343][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:41:00,844][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:41:01,341][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:41:01,842][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:41:02,342][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:41:02,843][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:41:03,344][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:41:03,841][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:41:04,340][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:41:04,838][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:41:05,337][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:41:05,834][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:41:06,333][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:41:06,830][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:41:07,329][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:41:07,828][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:41:08,325][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:41:08,822][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:41:09,321][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:41:09,823][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:41:10,321][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:41:10,822][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:41:11,321][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:41:11,824][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:41:12,325][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:41:12,825][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:41:13,325][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:41:13,823][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:41:14,321][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:41:14,819][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:41:15,318][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:41:15,820][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:41:16,322][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:41:16,823][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:41:17,323][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:41:17,824][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:41:18,324][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:41:18,825][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:41:19,325][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:41:19,826][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:41:20,324][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:41:20,825][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:41:21,325][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:41:21,823][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:41:22,322][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:41:22,820][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:41:23,321][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:41:23,821][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:41:24,321][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:41:24,822][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:41:25,324][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:41:25,825][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:41:26,323][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:41:26,825][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:41:27,326][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:41:27,823][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:41:28,322][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:41:28,821][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:41:29,319][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:41:29,817][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:41:30,315][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:41:30,814][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:41:31,311][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:41:31,811][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:41:32,312][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:41:32,811][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:41:33,309][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:41:33,813][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:41:34,318][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:41:34,818][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:41:35,320][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:41:35,819][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:41:36,318][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:41:36,820][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:41:37,319][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:41:37,817][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:41:38,316][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:41:38,815][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:41:39,314][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21015 tokens. [2026-03-25 16:41:40,478][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.11%, Current % of VRAM taken: 60.47%, Block Peak % of device VRAM: 62.17%, ΔTime: 00:01:07 [2026-03-25 16:41:41,227][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:41:41,229][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:41:41,231][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:41:42,042][__main__][INFO] - Iteration 42 took 1m 26s (15.54% Gen, 83.52% Train). Generation: 13s, Training: 1m 11s. Estimated remaining time: 70h 43m 15s. Estimated total time: 71h 49m 43s. Time estimates for 10 more iterations: 14m 21s, 100 more iterations: 2h 23m 39s, 500 more iterations: 11h 58m 17s. [2026-03-25 16:41:42,048][__main__][INFO] - Starting iteration 42. [2026-03-25 16:41:43,725][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:41:43,725][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:41:44,882][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:41:57,548][__main__][INFO] - Number of regex retries in iteration 42: 1 [2026-03-25 16:41:57,549][__main__][INFO] - agents played in iteration 42 are Bob, Alice [2026-03-25 16:41:59,600][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:42:00,665][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:42:02,280][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:42:03,406][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:42:03,906][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:42:04,406][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:42:04,906][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:42:05,900][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:42:06,403][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:42:06,902][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:42:07,656][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:42:08,523][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:42:09,024][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:42:09,525][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:42:10,027][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:42:10,529][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:42:11,034][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:42:11,536][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:42:12,038][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:42:12,539][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:42:13,040][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:42:13,541][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:42:14,041][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:42:14,540][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:42:15,040][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:42:15,540][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:42:16,052][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:42:16,551][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:42:17,051][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:42:17,553][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:42:18,052][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:42:18,549][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:42:19,046][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:42:19,545][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:42:20,046][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:42:20,546][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:42:21,046][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:42:21,546][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:42:22,042][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:42:22,541][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:42:23,043][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:42:23,544][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:42:24,039][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:42:24,536][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:42:25,035][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:42:25,531][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:42:26,029][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:42:26,525][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:42:27,022][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:42:27,519][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:42:28,017][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:42:28,513][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:42:29,014][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:42:29,510][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:42:30,007][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:42:30,505][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:42:31,005][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:42:31,505][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:42:32,006][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:42:32,507][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:42:33,008][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:42:33,508][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:42:34,009][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:42:34,508][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:42:35,006][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:42:35,506][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:42:36,004][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:42:36,501][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:42:37,001][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:42:37,501][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:42:38,003][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:42:38,504][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:42:39,005][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:42:39,505][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:42:40,007][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:42:40,743][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:42:41,247][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:42:41,748][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:42:42,250][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:42:42,755][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:42:43,260][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:42:43,762][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:42:44,262][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:42:44,762][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:42:45,261][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:42:45,761][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:42:46,261][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:42:46,760][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:42:47,260][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:42:47,760][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:42:48,258][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:42:48,759][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:42:49,256][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:42:49,757][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:42:50,255][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:42:50,754][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:42:51,253][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:42:51,752][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:42:52,250][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:42:52,750][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:42:53,249][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:42:53,747][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:42:54,245][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:42:54,743][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:42:55,244][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:42:55,743][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:42:56,239][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:42:56,735][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:42:57,231][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:42:57,728][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:42:58,224][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:42:58,721][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:42:59,218][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:42:59,716][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:43:00,216][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:43:00,713][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:43:01,210][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:43:01,707][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:43:02,204][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:43:02,702][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:43:03,201][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:43:03,699][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:43:04,199][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:43:04,700][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:43:05,200][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:43:05,700][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:43:06,201][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:43:06,698][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:43:07,199][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:43:07,698][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20507 tokens. [2026-03-25 16:43:09,499][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.12%, Current % of VRAM taken: 60.48%, Block Peak % of device VRAM: 62.47%, ΔTime: 00:01:08 [2026-03-25 16:43:10,237][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:43:10,239][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:43:10,240][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:43:11,062][__main__][INFO] - Iteration 43 took 1m 27s (15.83% Gen, 83.23% Train). Generation: 13s, Training: 1m 12s. Estimated remaining time: 71h 39m 8s. Estimated total time: 72h 47m 6s. Time estimates for 10 more iterations: 14m 33s, 100 more iterations: 2h 25m 34s, 500 more iterations: 12h 7m 51s. [2026-03-25 16:43:11,064][__main__][INFO] - Starting iteration 43. [2026-03-25 16:43:12,734][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:43:12,735][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:43:26,158][__main__][INFO] - Number of regex retries in iteration 43: 0 [2026-03-25 16:43:26,159][__main__][INFO] - agents played in iteration 43 are Bob, Alice [2026-03-25 16:43:28,443][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:43:29,511][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:43:31,124][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:43:32,249][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:43:33,015][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:43:33,517][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:43:34,017][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:43:34,517][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:43:35,016][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:43:35,517][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:43:36,499][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:43:37,369][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:43:38,231][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:43:38,733][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:43:39,235][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:43:39,737][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:43:40,239][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:43:40,740][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:43:41,240][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:43:41,741][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:43:42,239][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:43:42,741][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:43:43,240][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:43:43,741][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:43:44,242][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:43:44,743][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:43:45,243][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:43:45,743][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:43:46,242][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:43:46,743][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:43:47,242][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:43:47,740][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:43:48,238][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:43:48,738][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:43:49,244][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:43:49,745][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:43:50,246][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:43:50,747][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:43:51,249][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:43:51,749][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:43:52,250][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:43:52,751][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:43:53,248][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:43:53,746][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:43:54,244][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:43:54,743][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:43:55,242][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:43:55,742][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:43:56,240][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:43:56,738][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:43:57,240][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:43:57,740][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:43:58,242][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:43:58,740][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:43:59,242][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:43:59,743][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:44:00,240][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:44:00,741][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:44:01,241][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:44:01,742][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:44:02,242][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:44:02,743][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:44:03,242][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:44:03,742][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:44:04,242][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:44:04,742][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:44:05,238][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:44:05,736][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:44:06,233][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:44:06,730][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:44:07,230][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:44:07,727][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:44:08,225][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:44:08,724][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:44:09,225][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:44:09,727][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:44:10,229][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:44:10,730][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:44:11,232][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:44:11,741][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:44:12,243][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:44:12,744][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:44:13,244][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:44:13,740][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:44:14,241][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:44:14,742][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:44:15,240][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:44:15,741][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:44:16,241][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:44:16,741][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:44:17,241][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:44:17,740][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:44:18,241][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:44:18,742][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:44:19,243][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:44:19,743][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:44:20,241][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:44:20,739][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:44:21,241][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:44:21,742][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:44:22,243][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:44:22,744][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:44:23,245][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:44:24,276][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:44:24,781][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:44:25,281][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:44:25,782][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:44:26,282][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:44:26,782][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:44:27,282][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:44:27,780][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:44:28,281][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:44:28,781][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:44:29,282][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:44:29,780][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:44:30,282][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:44:30,782][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:44:31,283][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:44:31,783][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:44:32,284][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:44:32,784][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:44:33,284][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:44:33,784][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:44:34,282][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:44:34,784][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:44:35,284][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:44:35,782][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:44:36,280][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:44:36,779][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:44:37,279][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20938 tokens. [2026-03-25 16:44:38,348][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.27%, ΔTime: 00:01:08 [2026-03-25 16:44:39,089][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:44:39,091][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:44:39,092][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:44:39,871][__main__][INFO] - Iteration 44 took 1m 27s (15.41% Gen, 83.70% Train). Generation: 13s, Training: 1m 12s. Estimated remaining time: 71h 27m 27s. Estimated total time: 72h 36m 54s. Time estimates for 10 more iterations: 14m 31s, 100 more iterations: 2h 25m 13s, 500 more iterations: 12h 6m 9s. [2026-03-25 16:44:39,873][__main__][INFO] - Starting iteration 44. [2026-03-25 16:44:41,544][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:44:41,545][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:44:42,830][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:44:55,684][__main__][INFO] - Number of regex retries in iteration 44: 1 [2026-03-25 16:44:55,685][__main__][INFO] - agents played in iteration 44 are Bob, Alice [2026-03-25 16:44:58,172][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:44:59,240][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:45:00,851][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:45:01,980][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:45:02,731][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:45:03,233][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:45:03,736][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:45:04,237][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:45:05,206][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:45:05,708][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:45:06,210][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:45:06,713][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:45:07,216][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:45:07,719][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:45:08,220][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:45:08,722][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:45:09,562][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:45:10,526][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:45:11,450][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:45:11,955][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:45:12,457][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:45:12,959][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:45:13,462][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:45:14,056][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:45:14,559][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:45:15,060][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:45:15,561][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:45:16,063][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:45:16,564][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:45:17,066][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:45:17,567][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:45:18,070][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:45:18,572][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:45:19,076][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:45:19,576][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:45:20,075][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:45:20,576][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:45:21,077][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:45:21,577][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:45:22,077][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:45:22,577][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:45:23,078][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:45:23,579][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:45:24,079][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:45:24,580][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:45:25,080][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:45:25,581][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:45:26,081][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:45:26,583][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:45:27,083][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:45:27,584][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:45:28,086][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:45:28,586][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:45:29,087][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:45:29,584][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:45:30,087][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:45:30,587][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:45:31,085][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:45:31,584][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:45:32,085][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:45:32,587][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:45:33,089][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:45:33,590][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:45:34,091][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:45:34,589][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:45:35,090][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:45:35,592][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:45:36,094][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:45:36,596][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:45:37,097][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:45:37,599][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:45:38,110][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:45:38,613][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:45:39,116][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:45:39,619][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:45:40,121][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:45:40,624][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:45:41,126][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:45:41,628][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:45:42,129][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:45:42,631][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:45:43,134][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:45:43,636][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:45:44,139][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:45:44,642][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:45:45,143][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:45:45,644][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:45:46,146][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:45:46,648][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:45:47,149][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:45:47,650][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:45:48,153][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:45:48,657][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:45:49,159][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:45:49,661][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:45:50,162][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:45:50,664][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:45:51,167][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:45:51,664][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:45:52,163][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:45:52,662][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:45:53,161][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:45:53,660][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:45:54,159][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:45:54,658][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:45:55,156][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:45:55,658][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:45:56,158][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:45:56,658][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:45:57,159][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:45:57,660][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:45:58,159][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:45:58,661][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:45:59,159][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:45:59,659][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:46:00,157][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:46:00,657][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:46:01,158][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:46:01,658][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:46:02,159][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:46:02,657][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:46:03,156][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:46:03,658][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:46:04,160][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:46:04,663][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:46:05,163][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:46:05,663][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:46:06,163][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:46:06,664][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:46:07,167][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21008 tokens. [2026-03-25 16:46:08,939][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:09 [2026-03-25 16:46:09,674][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:46:09,676][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:46:09,678][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:46:10,523][__main__][INFO] - Iteration 45 took 1m 28s (15.89% Gen, 83.16% Train). Generation: 14s, Training: 1m 13s. Estimated remaining time: 72h 58m 1s. Estimated total time: 74h 8m 59s. Time estimates for 10 more iterations: 14m 49s, 100 more iterations: 2h 28m 17s, 500 more iterations: 12h 21m 29s. [2026-03-25 16:46:10,525][__main__][INFO] - Starting iteration 45. [2026-03-25 16:46:12,198][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:46:12,198][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:46:24,814][__main__][INFO] - Number of regex retries in iteration 45: 0 [2026-03-25 16:46:24,815][__main__][INFO] - agents played in iteration 45 are Bob, Alice [2026-03-25 16:46:27,015][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:46:28,085][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:46:29,696][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:46:30,825][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:46:31,326][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:46:31,827][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:46:32,329][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:46:32,829][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:46:33,329][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:46:34,205][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:46:34,705][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:46:35,207][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:46:35,715][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:46:36,218][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:46:36,720][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:46:37,222][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:46:37,723][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:46:38,224][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:46:38,724][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:46:39,222][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:46:40,161][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:46:40,660][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:46:41,159][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:46:41,899][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:46:42,398][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:46:42,898][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:46:43,399][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:46:43,901][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:46:44,403][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:46:44,904][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:46:45,405][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:46:45,906][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:46:46,406][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:46:46,907][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:46:47,405][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:46:47,905][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:46:48,403][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:46:48,904][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:46:49,402][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:46:49,902][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:46:50,401][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:46:50,901][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:46:51,626][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:46:52,487][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:46:52,989][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:46:53,490][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:46:53,994][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:46:54,496][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:46:54,999][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:46:55,502][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:46:56,002][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:46:56,501][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:46:56,999][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:46:57,500][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:46:57,999][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:46:58,501][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:46:59,002][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:46:59,503][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:47:00,004][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:47:00,501][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:47:01,003][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:47:01,504][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:47:02,002][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:47:02,501][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:47:03,001][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:47:03,502][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:47:04,004][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:47:04,504][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:47:05,005][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:47:05,505][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:47:06,003][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:47:06,503][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:47:07,004][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:47:07,505][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:47:08,006][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:47:08,507][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:47:09,010][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:47:09,511][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:47:10,011][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:47:10,514][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:47:11,015][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:47:11,515][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:47:12,018][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:47:12,516][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:47:13,015][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:47:13,515][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:47:14,015][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:47:14,514][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:47:15,013][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:47:15,512][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:47:16,013][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:47:16,514][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:47:17,016][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:47:17,516][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:47:18,017][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:47:18,518][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:47:19,019][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:47:19,519][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:47:20,018][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:47:20,517][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:47:21,017][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:47:21,516][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:47:22,016][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:47:22,515][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:47:23,014][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:47:23,513][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:47:24,015][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:47:24,717][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:47:25,220][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:47:25,721][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:47:26,223][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:47:26,724][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:47:27,225][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:47:27,726][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:47:28,226][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:47:28,724][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:47:29,222][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:47:29,723][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:47:30,221][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:47:30,723][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:47:31,223][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:47:31,724][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:47:32,225][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:47:32,727][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:47:33,228][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:47:33,729][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:47:34,228][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:47:34,730][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:47:35,231][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:47:35,733][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21033 tokens. [2026-03-25 16:47:36,930][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:08 [2026-03-25 16:47:37,659][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:47:37,662][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:47:37,663][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:47:38,414][__main__][INFO] - Iteration 46 took 1m 26s (14.63% Gen, 84.49% Train). Generation: 12s, Training: 1m 12s. Estimated remaining time: 70h 38m 24s. Estimated total time: 71h 50m 49s. Time estimates for 10 more iterations: 14m 22s, 100 more iterations: 2h 23m 41s, 500 more iterations: 11h 58m 28s. [2026-03-25 16:47:38,416][__main__][INFO] - Starting iteration 46. [2026-03-25 16:47:39,447][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:47:39,448][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:47:48,303][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:47:52,074][__main__][INFO] - Number of regex retries in iteration 46: 1 [2026-03-25 16:47:52,075][__main__][INFO] - agents played in iteration 46 are Bob, Alice [2026-03-25 16:47:54,134][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:47:55,203][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:47:56,814][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:47:57,940][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:47:58,707][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:47:59,208][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:47:59,708][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:48:00,208][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:48:00,708][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:48:01,208][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:48:01,709][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:48:02,209][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:48:02,706][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:48:03,206][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:48:03,703][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:48:04,203][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:48:04,703][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:48:05,203][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:48:05,705][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:48:06,538][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:48:07,039][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:48:07,538][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:48:08,040][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:48:09,142][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:48:09,642][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:48:10,144][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:48:10,644][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:48:11,145][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:48:11,647][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:48:12,150][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:48:12,650][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:48:13,150][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:48:13,652][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:48:14,154][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:48:14,655][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:48:15,156][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:48:15,657][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:48:16,158][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:48:16,657][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:48:17,158][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:48:17,658][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:48:18,159][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:48:18,661][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:48:19,163][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:48:19,662][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:48:20,163][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:48:20,663][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:48:21,163][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:48:21,664][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:48:22,166][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:48:23,111][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:48:23,961][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:48:24,463][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:48:24,965][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:48:25,465][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:48:26,573][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:48:27,075][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:48:27,575][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:48:28,075][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:48:28,574][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:48:29,074][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:48:29,573][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:48:30,072][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:48:30,572][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:48:31,072][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:48:31,571][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:48:32,071][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:48:32,572][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:48:33,072][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:48:33,570][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:48:34,069][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:48:34,571][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:48:35,067][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:48:35,569][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:48:36,069][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:48:36,576][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:48:37,079][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:48:37,581][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:48:38,079][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:48:38,581][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:48:39,081][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:48:39,580][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:48:40,081][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:48:40,582][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:48:41,082][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:48:41,585][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:48:42,086][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:48:42,586][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:48:43,086][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:48:43,587][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:48:44,086][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:48:44,587][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:48:45,088][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:48:45,590][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:48:46,092][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:48:46,593][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:48:47,096][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:48:47,598][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:48:48,099][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:48:48,602][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:48:49,103][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:48:49,603][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:48:50,104][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:48:50,605][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:48:51,105][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:48:51,606][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:48:52,107][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:48:52,609][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:48:53,110][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:48:53,611][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:48:54,114][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:48:54,615][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:48:55,118][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:48:55,619][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:48:56,120][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:48:56,935][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:48:57,436][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:48:57,937][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:48:58,439][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:48:58,941][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:48:59,441][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:48:59,942][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:49:00,441][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:49:00,941][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:49:01,441][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:49:01,939][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:49:02,439][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:49:02,940][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:49:03,439][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:49:03,937][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21199 tokens. [2026-03-25 16:49:04,914][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.15%, Current % of VRAM taken: 60.51%, Block Peak % of device VRAM: 62.25%, ΔTime: 00:01:09 [2026-03-25 16:49:05,650][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:49:05,652][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:49:05,654][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:49:06,291][__main__][INFO] - Iteration 47 took 1m 26s (14.54% Gen, 84.73% Train). Generation: 12s, Training: 1m 13s. Estimated remaining time: 71h 8m 19s. Estimated total time: 72h 22m 12s. Time estimates for 10 more iterations: 14m 28s, 100 more iterations: 2h 24m 44s, 500 more iterations: 12h 3m 42s. [2026-03-25 16:49:06,293][__main__][INFO] - Starting iteration 47. [2026-03-25 16:49:07,381][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:49:07,382][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:49:08,415][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:49:11,903][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:49:17,724][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:49:20,494][__main__][INFO] - Number of regex retries in iteration 47: 3 [2026-03-25 16:49:20,495][__main__][INFO] - agents played in iteration 47 are Bob, Alice [2026-03-25 16:49:23,008][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:49:24,078][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:49:25,687][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:49:26,822][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:49:27,577][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:49:28,079][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:49:28,582][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:49:29,085][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:49:29,585][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:49:30,178][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:49:30,678][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:49:31,180][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:49:31,681][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:49:32,183][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:49:32,684][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:49:33,185][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:49:33,686][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:49:34,187][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:49:34,687][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:49:35,188][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:49:35,689][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:49:36,191][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:49:36,694][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:49:37,196][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:49:37,697][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:49:38,199][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:49:38,700][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:49:39,202][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:49:39,705][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:49:40,206][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:49:40,708][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:49:41,209][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:49:41,714][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:49:42,216][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:49:42,716][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:49:43,216][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:49:43,715][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:49:44,213][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:49:44,713][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:49:45,212][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:49:45,711][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:49:46,210][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:49:46,710][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:49:47,212][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:49:47,712][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:49:48,212][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:49:48,714][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:49:49,216][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:49:49,717][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:49:50,218][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:49:50,721][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:49:51,833][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:49:52,335][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:49:52,838][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:49:53,342][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:49:53,843][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:49:54,345][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:49:54,848][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:49:55,350][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:49:55,852][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:49:56,354][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:49:56,857][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:49:57,358][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:49:57,860][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:49:58,361][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:49:58,863][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:49:59,364][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:49:59,867][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:50:00,367][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:50:00,869][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:50:01,370][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:50:01,875][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:50:02,376][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:50:02,879][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:50:03,380][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:50:03,881][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:50:04,382][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:50:04,883][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:50:05,384][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:50:05,887][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:50:06,387][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:50:06,887][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:50:07,387][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:50:07,888][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:50:08,389][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:50:08,890][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:50:09,391][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:50:09,892][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:50:10,391][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:50:10,893][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:50:11,398][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:50:11,900][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:50:12,402][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:50:12,903][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:50:13,405][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:50:13,906][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:50:14,407][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:50:14,909][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:50:15,408][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:50:15,908][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:50:16,408][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:50:16,907][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:50:17,406][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:50:17,904][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:50:18,405][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:50:18,907][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:50:19,409][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:50:19,909][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:50:20,410][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:50:20,912][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:50:21,413][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:50:21,914][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:50:22,415][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:50:22,915][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:50:23,418][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:50:23,921][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:50:24,423][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:50:24,926][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:50:25,937][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:50:26,438][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:50:26,940][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:50:27,447][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:50:27,948][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:50:28,450][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:50:28,950][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:50:29,451][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:50:29,953][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:50:30,456][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:50:30,955][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:50:31,455][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21204 tokens. [2026-03-25 16:50:32,918][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:08 [2026-03-25 16:50:33,644][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:50:33,646][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:50:33,648][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:50:34,342][__main__][INFO] - Iteration 48 took 1m 26s (15.08% Gen, 84.12% Train). Generation: 13s, Training: 1m 13s. Estimated remaining time: 71h 12m 43s. Estimated total time: 72h 28m 4s. Time estimates for 10 more iterations: 14m 29s, 100 more iterations: 2h 24m 56s, 500 more iterations: 12h 4m 40s. [2026-03-25 16:50:34,344][__main__][INFO] - Starting iteration 48. [2026-03-25 16:50:35,386][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:50:35,387][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:50:48,762][__main__][INFO] - Number of regex retries in iteration 48: 0 [2026-03-25 16:50:48,763][__main__][INFO] - agents played in iteration 48 are Bob, Alice [2026-03-25 16:50:51,015][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:50:52,082][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:50:53,695][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:50:54,824][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:50:55,327][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:50:55,828][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:50:56,329][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:50:56,830][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:50:57,331][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:50:57,833][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:50:58,333][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:50:58,832][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:50:59,806][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:51:00,306][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:51:00,807][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:51:01,309][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:51:01,810][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:51:02,309][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:51:03,419][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:51:03,920][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:51:05,026][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:51:06,028][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:51:06,530][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:51:07,027][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:51:07,528][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:51:08,028][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:51:08,529][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:51:09,029][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:51:09,530][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:51:10,030][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:51:10,531][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:51:11,033][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:51:11,537][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:51:12,039][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:51:12,540][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:51:13,040][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:51:13,541][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:51:14,042][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:51:14,543][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:51:15,044][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:51:15,545][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:51:16,043][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:51:16,543][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:51:17,043][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:51:17,542][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:51:18,043][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:51:18,544][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:51:19,042][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:51:19,543][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:51:20,043][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:51:20,543][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:51:21,043][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:51:21,541][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:51:22,042][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:51:22,543][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:51:23,041][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:51:23,541][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:51:24,039][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:51:24,541][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:51:25,041][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:51:25,542][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:51:26,040][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:51:26,540][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:51:27,040][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:51:27,540][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:51:28,041][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:51:28,542][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:51:29,043][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:51:29,544][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:51:30,044][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:51:30,544][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:51:31,045][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:51:31,544][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:51:32,045][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:51:32,543][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:51:33,041][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:51:33,541][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:51:34,039][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:51:34,540][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:51:35,040][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:51:35,541][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:51:36,040][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:51:36,541][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:51:37,041][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:51:37,542][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:51:38,043][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:51:38,543][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:51:39,041][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:51:40,011][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:51:40,511][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:51:41,016][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:51:41,519][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:51:42,022][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:51:42,524][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:51:43,024][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:51:43,524][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:51:44,025][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:51:44,527][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:51:45,028][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:51:45,528][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:51:46,029][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:51:46,529][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:51:47,029][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:51:47,527][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:51:48,029][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:51:48,530][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:51:49,029][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:51:49,530][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:51:50,029][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:51:50,527][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:51:51,029][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:51:51,525][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:51:52,025][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:51:52,525][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:51:53,024][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:51:53,525][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:51:54,025][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:51:54,525][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:51:55,026][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:51:55,527][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:51:56,027][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:51:56,526][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:51:57,026][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:51:57,527][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:51:58,026][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:51:58,526][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:51:59,027][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:51:59,527][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:52:00,026][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:52:00,524][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21265 tokens. [2026-03-25 16:52:01,158][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.12%, Current % of VRAM taken: 60.48%, Block Peak % of device VRAM: 62.26%, ΔTime: 00:01:09 [2026-03-25 16:52:01,885][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:52:01,888][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:52:01,889][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:52:02,563][__main__][INFO] - Iteration 49 took 1m 27s (15.34% Gen, 83.88% Train). Generation: 13s, Training: 1m 13s. Estimated remaining time: 71h 22m 0s. Estimated total time: 72h 38m 50s. Time estimates for 10 more iterations: 14m 31s, 100 more iterations: 2h 25m 17s, 500 more iterations: 12h 6m 28s. [2026-03-25 16:52:02,565][__main__][INFO] - Starting iteration 49. [2026-03-25 16:52:02,965][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:52:02,966][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:52:03,639][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:52:15,174][__main__][INFO] - Number of regex retries in iteration 49: 1 [2026-03-25 16:52:15,175][__main__][INFO] - agents played in iteration 49 are Bob, Alice [2026-03-25 16:52:16,010][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:52:16,612][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:52:17,069][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:52:17,575][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:52:18,077][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:52:18,573][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:52:19,070][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:52:19,566][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:52:20,066][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:52:20,567][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:52:21,067][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:52:21,567][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:52:22,067][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:52:22,566][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:52:23,066][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:52:23,565][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:52:24,066][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:52:24,565][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:52:25,066][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:52:25,566][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:52:26,063][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:52:26,566][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:52:27,066][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:52:27,567][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:52:28,067][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:52:28,567][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:52:29,067][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:52:29,566][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:52:30,065][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:52:30,565][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:52:31,066][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:52:31,566][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:52:32,062][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:52:32,561][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:52:33,060][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:52:33,561][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:52:34,060][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:52:34,561][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:52:35,058][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:52:35,560][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:52:36,058][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:52:36,559][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:52:37,059][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:52:37,558][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:52:38,059][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:52:38,558][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:52:39,058][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:52:39,556][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:52:40,055][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:52:40,556][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:52:41,056][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:52:41,558][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:52:42,058][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:52:42,558][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:52:43,058][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:52:43,555][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:52:44,056][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:52:44,557][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:52:45,053][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:52:45,550][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:52:46,050][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:52:46,547][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:52:47,045][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:52:47,542][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:52:48,040][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:52:48,540][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:52:49,041][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:52:49,541][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:52:50,040][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:52:50,541][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:52:51,042][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:52:51,543][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:52:52,043][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:52:52,544][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:52:53,044][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:52:53,544][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:52:54,044][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:52:54,544][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:52:55,044][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:52:55,544][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:52:56,044][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:52:56,544][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:52:57,041][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:52:57,541][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:52:58,038][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:52:58,540][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:52:59,040][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:52:59,541][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:53:00,041][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:53:00,542][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:53:01,042][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:53:01,543][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:53:02,043][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:53:02,543][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:53:03,043][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:53:03,543][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:53:04,042][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:53:04,543][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:53:05,043][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:53:05,543][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:53:06,043][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:53:06,544][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:53:07,044][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:53:07,544][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:53:08,042][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:53:08,543][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:53:09,044][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:53:09,544][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:53:10,042][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:53:10,543][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:53:11,043][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:53:11,544][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:53:12,043][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:53:12,544][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:53:13,044][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:53:13,544][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:53:14,044][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:53:14,542][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:53:15,040][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:53:15,541][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:53:16,038][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:53:16,538][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:53:17,037][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:53:17,537][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:53:18,039][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:53:18,536][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:53:19,034][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:53:19,530][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:53:20,029][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:53:20,526][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21136 tokens. [2026-03-25 16:53:21,518][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.12%, Current % of VRAM taken: 60.48%, Block Peak % of device VRAM: 62.16%, ΔTime: 00:01:04 [2026-03-25 16:53:22,245][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:53:22,247][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:53:22,249][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:53:22,879][__main__][INFO] - Iteration 50 took 1m 19s (15.28% Gen, 83.93% Train). Generation: 12s, Training: 1m 7s. Estimated remaining time: 65h 17m 33s. Estimated total time: 66h 35m 43s. Time estimates for 10 more iterations: 13m 19s, 100 more iterations: 2h 13m 11s, 500 more iterations: 11h 5m 57s. [2026-03-25 16:53:22,881][__main__][INFO] - Starting iteration 50. [2026-03-25 16:53:23,991][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 0 and human policies 1. [2026-03-25 16:53:23,992][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:53:35,271][__main__][INFO] - Number of regex retries in iteration 50: 0 [2026-03-25 16:53:35,272][__main__][INFO] - agents played in iteration 50 are Bob, Alice [2026-03-25 16:53:37,873][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:53:38,937][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:53:40,552][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:53:42,307][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:53:43,305][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:53:43,806][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:53:44,921][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:53:45,919][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:53:46,418][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:53:46,919][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:53:47,671][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:53:48,533][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:53:49,035][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:53:49,536][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:53:50,036][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:53:50,536][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:53:51,037][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:53:51,538][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:53:52,068][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:53:52,569][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:53:53,070][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:53:53,572][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:53:54,073][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:53:54,573][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:53:55,075][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:53:55,576][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:53:56,077][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:53:56,577][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:53:57,078][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:53:57,576][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:53:58,074][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:53:58,575][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:53:59,072][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:53:59,573][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:54:00,073][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:54:00,573][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:54:01,075][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:54:01,575][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:54:02,072][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:54:02,573][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:54:03,073][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:54:03,573][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:54:04,221][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:54:05,083][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:54:05,955][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:54:06,457][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:54:06,959][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:54:07,461][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:54:07,963][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:54:08,465][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:54:08,962][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:54:09,463][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:54:09,960][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:54:10,458][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:54:10,959][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:54:11,461][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:54:11,960][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:54:12,459][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:54:12,960][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:54:13,461][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:54:13,962][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:54:14,463][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:54:14,963][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:54:15,463][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:54:15,961][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:54:16,462][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:54:16,960][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:54:17,459][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:54:17,958][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:54:18,456][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:54:18,955][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:54:19,453][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:54:19,950][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:54:20,448][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:54:20,949][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:54:21,449][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:54:21,949][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:54:22,449][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:54:22,948][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:54:23,448][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:54:23,948][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:54:24,448][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:54:24,948][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:54:25,449][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:54:25,949][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:54:26,450][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:54:26,949][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:54:27,449][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:54:27,950][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:54:28,451][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:54:28,950][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:54:29,450][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:54:29,950][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:54:30,450][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:54:30,950][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:54:31,450][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:54:31,950][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:54:32,450][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:54:32,948][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:54:33,450][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:54:33,949][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:54:34,449][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:54:34,947][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:54:35,447][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:54:35,946][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:54:36,445][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:54:36,948][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:54:37,449][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:54:38,059][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:54:38,561][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:54:39,062][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:54:39,564][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:54:40,066][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:54:40,568][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:54:41,069][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:54:41,571][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:54:42,069][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:54:42,571][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:54:43,071][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:54:43,572][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:54:44,070][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:54:44,571][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:54:45,070][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:54:45,571][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:54:46,071][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:54:46,573][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:54:47,073][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:54:47,575][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:54:48,076][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:54:48,578][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21374 tokens. [2026-03-25 16:54:50,410][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:11 [2026-03-25 16:54:51,135][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:54:51,137][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:54:51,138][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:54:52,795][__main__][INFO] - Iteration 51 took 1m 28s (12.70% Gen, 85.43% Train). Generation: 11s, Training: 1m 15s. Estimated remaining time: 72h 40m 35s. Estimated total time: 74h 0m 15s. Time estimates for 10 more iterations: 14m 48s, 100 more iterations: 2h 28m 0s, 500 more iterations: 12h 20m 2s. [2026-03-25 16:54:52,797][__main__][INFO] - Starting iteration 51. [2026-03-25 16:54:54,467][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 16:54:54,468][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:55:05,700][__main__][INFO] - Number of regex retries in iteration 51: 0 [2026-03-25 16:55:05,701][__main__][INFO] - agents played in iteration 51 are Bob, Alice [2026-03-25 16:55:07,620][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:55:08,686][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:55:10,299][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:55:11,428][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:55:11,929][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:55:12,431][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:55:12,932][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:55:13,432][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:55:13,935][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:55:14,437][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:55:14,939][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:55:15,440][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:55:15,940][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:55:16,441][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:55:16,941][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:55:17,440][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:55:18,278][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:55:18,779][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:55:19,277][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:55:20,026][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:55:20,527][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:55:21,028][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:55:21,528][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:55:22,028][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:55:22,528][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:55:23,028][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:55:23,529][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:55:24,029][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:55:24,530][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:55:25,030][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:55:25,530][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:55:26,029][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:55:26,529][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:55:27,029][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:55:27,874][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:55:28,735][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:55:29,237][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:55:29,740][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:55:30,242][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:55:30,744][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:55:31,247][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:55:31,749][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:55:32,250][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:55:32,751][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:55:33,253][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:55:33,756][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:55:34,258][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:55:34,758][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:55:35,260][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:55:35,760][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:55:36,261][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:55:36,762][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:55:37,263][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:55:37,761][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:55:38,263][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:55:38,763][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:55:39,263][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:55:39,763][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:55:40,263][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:55:40,764][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:55:41,265][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:55:41,766][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:55:42,267][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:55:42,764][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:55:43,265][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:55:43,765][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:55:44,266][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:55:44,766][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:55:45,265][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:55:45,765][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:55:46,264][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:55:46,763][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:55:47,263][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:55:47,763][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:55:48,263][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:55:48,765][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:55:49,266][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:55:49,766][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:55:50,266][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:55:50,767][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:55:51,268][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:55:51,769][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:55:52,271][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:55:52,772][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:55:53,276][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:55:53,777][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:55:54,280][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:55:54,781][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:55:55,283][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:55:55,784][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:55:56,285][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:55:56,787][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:55:57,288][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:55:57,789][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:55:58,290][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:55:58,791][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:55:59,293][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:55:59,795][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:56:00,298][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:56:00,802][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:56:01,305][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:56:01,808][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:56:02,311][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:56:02,814][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:56:03,316][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:56:04,347][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:56:05,287][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:56:05,789][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:56:06,292][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:56:06,797][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:56:07,299][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:56:07,803][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:56:08,306][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:56:08,809][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:56:09,311][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:56:09,814][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:56:10,314][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:56:10,816][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:56:11,320][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:56:11,823][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:56:12,325][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:56:12,827][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:56:13,329][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:56:13,830][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:56:14,331][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:56:14,834][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:56:15,335][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:56:15,836][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:56:16,336][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:56:16,836][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21494 tokens. [2026-03-25 16:56:18,403][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:09 [2026-03-25 16:56:19,139][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:56:19,142][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:56:19,143][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:56:19,779][__main__][INFO] - Iteration 52 took 1m 25s (13.17% Gen, 86.09% Train). Generation: 11s, Training: 1m 13s. Estimated remaining time: 69h 44m 31s. Estimated total time: 71h 5m 37s. Time estimates for 10 more iterations: 14m 13s, 100 more iterations: 2h 22m 11s, 500 more iterations: 11h 50m 56s. [2026-03-25 16:56:19,782][__main__][INFO] - Starting iteration 52. [2026-03-25 16:56:20,875][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 16:56:20,876][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:56:21,889][mllm.models.large_language_model_local][WARNING] - Response Proposal: 5 hats, 10 books, 5 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:56:27,435][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 16:56:32,699][__main__][INFO] - Number of regex retries in iteration 52: 2 [2026-03-25 16:56:32,700][__main__][INFO] - agents played in iteration 52 are Bob, Alice [2026-03-25 16:56:34,755][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:56:35,823][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:56:37,439][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:56:38,570][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:56:39,070][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:56:39,567][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:56:40,064][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:56:41,072][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:56:41,572][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:56:42,073][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:56:42,809][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:56:43,307][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:56:43,808][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:56:44,555][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:56:45,055][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:56:45,552][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:56:46,051][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:56:46,553][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:56:47,051][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:56:47,549][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:56:48,047][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:56:48,549][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:56:49,047][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:56:49,548][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:56:50,644][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:56:51,146][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:56:51,647][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:56:52,416][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:56:53,260][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:56:53,762][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:56:54,264][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:56:54,766][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:56:55,266][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:56:55,768][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:56:56,268][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:56:56,769][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:56:57,270][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:56:57,771][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:56:58,271][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:56:58,773][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:56:59,275][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:56:59,777][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:57:00,278][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:57:00,779][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:57:01,279][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:57:01,779][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:57:02,280][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:57:02,780][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:57:03,281][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:57:03,782][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:57:04,283][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:57:04,783][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:57:05,284][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:57:05,785][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:57:06,286][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:57:06,787][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:57:07,287][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:57:07,787][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:57:08,287][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:57:08,786][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:57:09,286][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:57:09,815][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:57:10,315][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:57:10,816][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:57:11,317][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:57:11,820][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:57:12,317][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:57:12,815][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:57:13,313][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:57:13,812][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:57:14,311][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:57:14,809][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:57:15,304][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:57:15,804][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:57:16,305][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:57:16,803][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:57:17,304][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:57:17,805][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:57:18,306][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:57:18,804][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:57:19,302][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:57:19,804][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:57:20,302][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:57:20,803][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:57:21,302][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:57:21,800][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:57:22,301][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:57:22,801][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:57:23,302][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:57:23,802][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:57:24,304][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:57:24,805][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:57:25,306][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:57:25,806][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:57:26,308][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:57:26,809][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:57:27,310][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:57:27,811][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:57:28,312][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:57:28,813][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:57:29,315][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:57:29,817][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:57:30,318][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:57:30,817][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:57:31,319][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:57:31,821][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:57:32,321][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:57:32,821][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:57:33,321][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:57:33,821][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:57:34,321][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:57:34,821][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:57:35,321][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:57:35,821][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:57:36,318][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:57:36,817][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:57:37,320][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:57:37,820][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:57:38,320][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:57:38,822][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:57:39,322][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:57:39,822][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:57:40,322][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:57:40,822][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:57:41,325][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:57:41,827][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:57:42,327][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:57:42,827][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:57:43,327][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:57:43,827][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 20968 tokens. [2026-03-25 16:57:45,529][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.19%, ΔTime: 00:01:09 [2026-03-25 16:57:46,267][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:57:46,269][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:57:46,271][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:57:46,928][__main__][INFO] - Iteration 53 took 1m 26s (13.74% Gen, 85.49% Train). Generation: 11s, Training: 1m 13s. Estimated remaining time: 70h 20m 8s. Estimated total time: 71h 42m 41s. Time estimates for 10 more iterations: 14m 20s, 100 more iterations: 2h 23m 25s, 500 more iterations: 11h 57m 6s. [2026-03-25 16:57:46,931][__main__][INFO] - Starting iteration 53. [2026-03-25 16:57:47,998][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 16:57:47,998][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:57:59,453][__main__][INFO] - Number of regex retries in iteration 53: 0 [2026-03-25 16:57:59,454][__main__][INFO] - agents played in iteration 53 are Bob, Alice [2026-03-25 16:58:01,874][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:58:02,938][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:58:04,553][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:58:05,682][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:58:06,394][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:58:06,897][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:58:07,420][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:58:07,922][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:58:08,424][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:58:08,927][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:58:09,428][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:58:09,930][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:58:10,432][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:58:10,933][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:58:11,436][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:58:11,940][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:58:12,442][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:58:12,944][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:58:13,447][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:58:14,266][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:58:14,768][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:58:15,270][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:58:15,771][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:58:16,272][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:58:16,777][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:58:17,279][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:58:17,780][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:58:18,282][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:58:18,783][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:58:19,286][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:58:19,787][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:58:20,287][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:58:20,789][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:58:21,290][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:58:21,792][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:58:22,293][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:58:22,795][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:58:23,297][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:58:23,798][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:58:24,300][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:58:24,801][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:58:25,303][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:58:25,804][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:58:26,304][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:58:26,806][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:58:27,306][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:58:27,807][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:58:28,307][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:58:28,807][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:58:29,307][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:58:29,807][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:58:30,308][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:58:30,808][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:58:31,307][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:58:31,805][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:58:32,306][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:58:32,805][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:58:33,304][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:58:33,808][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:58:34,309][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:58:34,810][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 16:58:35,310][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 16:58:35,810][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 16:58:36,311][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 16:58:36,810][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 16:58:37,311][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 16:58:37,812][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 16:58:38,313][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 16:58:38,814][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 16:58:39,316][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 16:58:39,818][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 16:58:40,319][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 16:58:40,820][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 16:58:41,324][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 16:58:41,827][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 16:58:42,328][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 16:58:42,828][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 16:58:43,329][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 16:58:43,830][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 16:58:44,330][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 16:58:44,830][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 16:58:45,332][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 16:58:45,835][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 16:58:46,337][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 16:58:46,839][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 16:58:47,340][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 16:58:47,842][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 16:58:48,344][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 16:58:48,846][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 16:58:49,348][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 16:58:49,849][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 16:58:50,351][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 16:58:50,853][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 16:58:51,356][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 16:58:51,857][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 16:58:52,359][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 16:58:52,861][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 16:58:53,363][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 16:58:53,863][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 16:58:54,364][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 16:58:54,864][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 16:58:55,365][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 16:58:55,865][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 16:58:56,367][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 16:58:56,867][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 16:58:57,369][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 16:58:57,869][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 16:58:58,371][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 16:58:58,871][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 16:58:59,372][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 16:58:59,872][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 16:59:00,373][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 16:59:00,874][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 16:59:01,375][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 16:59:01,876][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 16:59:02,373][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 16:59:02,869][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 16:59:03,369][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 16:59:03,865][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 16:59:04,365][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 16:59:04,862][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 16:59:05,363][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 16:59:05,865][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 16:59:06,364][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 16:59:06,865][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 16:59:07,365][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 16:59:07,864][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 16:59:08,364][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 16:59:08,863][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 16:59:09,364][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21409 tokens. [2026-03-25 16:59:10,876][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:07 [2026-03-25 16:59:11,609][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 16:59:11,611][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 16:59:11,612][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 16:59:12,295][__main__][INFO] - Iteration 54 took 1m 24s (13.59% Gen, 85.60% Train). Generation: 11s, Training: 1m 12s. Estimated remaining time: 68h 50m 53s. Estimated total time: 70h 14m 52s. Time estimates for 10 more iterations: 14m 2s, 100 more iterations: 2h 20m 29s, 500 more iterations: 11h 42m 28s. [2026-03-25 16:59:12,297][__main__][INFO] - Starting iteration 54. [2026-03-25 16:59:13,349][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 16:59:13,350][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 16:59:23,350][__main__][INFO] - Number of regex retries in iteration 54: 0 [2026-03-25 16:59:23,351][__main__][INFO] - agents played in iteration 54 are Bob, Alice [2026-03-25 16:59:25,486][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 16:59:26,553][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 16:59:28,169][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 16:59:29,298][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 16:59:29,799][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 16:59:30,799][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 16:59:31,300][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 16:59:31,802][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 16:59:32,303][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 16:59:32,805][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 16:59:33,544][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 16:59:34,402][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 16:59:34,905][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 16:59:35,408][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 16:59:36,143][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 16:59:36,645][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 16:59:37,758][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 16:59:38,259][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 16:59:38,757][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 16:59:39,257][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 16:59:39,757][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 16:59:40,257][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 16:59:40,755][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 16:59:41,256][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 16:59:41,758][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 16:59:42,257][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 16:59:42,758][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 16:59:43,260][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 16:59:43,815][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 16:59:44,317][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 16:59:44,821][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 16:59:45,323][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 16:59:45,825][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 16:59:46,326][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 16:59:46,827][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 16:59:47,327][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 16:59:47,827][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 16:59:48,327][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 16:59:48,827][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 16:59:49,327][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 16:59:49,827][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 16:59:50,327][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 16:59:50,826][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 16:59:51,326][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 16:59:51,827][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 16:59:52,327][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 16:59:52,828][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 16:59:53,329][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 16:59:53,830][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 16:59:54,329][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 16:59:54,829][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 16:59:55,330][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 16:59:55,831][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 16:59:56,331][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 16:59:56,832][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 16:59:57,332][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 16:59:57,833][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 16:59:58,333][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 16:59:58,836][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 16:59:59,337][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 16:59:59,839][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:00:00,339][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:00:00,840][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:00:01,341][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:00:01,842][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:00:02,343][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:00:02,844][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:00:03,344][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:00:03,842][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:00:04,342][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:00:04,842][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:00:05,342][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:00:05,842][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:00:06,341][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:00:06,842][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:00:07,342][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:00:07,843][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:00:08,344][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:00:08,843][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:00:09,344][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:00:09,846][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:00:10,346][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:00:10,843][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:00:11,344][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:00:11,845][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:00:12,345][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:00:12,843][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:00:13,344][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:00:13,843][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:00:14,343][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:00:14,844][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:00:15,344][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:00:15,845][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:00:16,346][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:00:16,847][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:00:17,347][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:00:17,848][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:00:18,349][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:00:18,850][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:00:19,350][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:00:19,850][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:00:20,351][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:00:20,851][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:00:21,351][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:00:21,851][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:00:22,353][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:00:22,853][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:00:23,354][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:00:23,855][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:00:24,355][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:00:24,857][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:00:25,358][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:00:25,858][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:00:26,359][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:00:26,859][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:00:27,359][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:00:27,860][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:00:28,360][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:00:28,861][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:00:29,361][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:00:29,861][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:00:30,362][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:00:30,863][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:00:31,364][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:00:31,863][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:00:32,364][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:00:32,864][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:00:33,365][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:00:33,866][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:00:34,367][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21582 tokens. [2026-03-25 17:00:35,386][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.33%, ΔTime: 00:01:08 [2026-03-25 17:00:36,015][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:00:36,018][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:00:36,019][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:00:36,637][__main__][INFO] - Iteration 55 took 1m 23s (12.01% Gen, 87.25% Train). Generation: 10s, Training: 1m 12s. Estimated remaining time: 67h 58m 59s. Estimated total time: 69h 24m 23s. Time estimates for 10 more iterations: 13m 52s, 100 more iterations: 2h 18m 48s, 500 more iterations: 11h 34m 3s. [2026-03-25 17:00:36,639][__main__][INFO] - Starting iteration 55. [2026-03-25 17:00:37,857][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:00:37,858][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:00:40,174][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:00:48,459][__main__][INFO] - Number of regex retries in iteration 55: 1 [2026-03-25 17:00:48,460][__main__][INFO] - agents played in iteration 55 are Bob, Alice [2026-03-25 17:00:50,863][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:00:51,924][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:00:53,542][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:00:54,668][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:00:55,169][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:00:55,670][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:00:56,171][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:00:56,673][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:00:57,175][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:00:57,676][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:00:58,177][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:00:58,784][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:00:59,285][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:00:59,785][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:01:00,285][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:01:00,785][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:01:01,286][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:01:01,788][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:01:02,289][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:01:02,792][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:01:03,294][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:01:03,796][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:01:04,297][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:01:04,799][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:01:05,300][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:01:05,801][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:01:06,303][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:01:06,807][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:01:07,617][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:01:08,119][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:01:08,621][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:01:09,123][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:01:09,625][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:01:10,127][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:01:10,628][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:01:11,129][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:01:11,631][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:01:12,134][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:01:12,636][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:01:13,138][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:01:13,639][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:01:14,141][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:01:14,642][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:01:15,144][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:01:15,646][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:01:16,147][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:01:16,649][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:01:17,149][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:01:17,651][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:01:18,152][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:01:18,948][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:01:19,807][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:01:20,312][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:01:20,817][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:01:21,321][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:01:21,824][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:01:22,327][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:01:22,832][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:01:23,334][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:01:23,834][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:01:24,334][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:01:24,834][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:01:25,334][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:01:25,834][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:01:26,335][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:01:26,836][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:01:27,337][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:01:27,839][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:01:28,340][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:01:28,842][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:01:29,343][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:01:29,845][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:01:30,347][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:01:30,848][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:01:31,347][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:01:31,848][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:01:32,348][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:01:32,849][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:01:33,350][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:01:33,850][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:01:34,351][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:01:34,851][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:01:35,351][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:01:35,853][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:01:36,354][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:01:36,856][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:01:37,356][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:01:37,858][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:01:38,359][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:01:38,860][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:01:39,363][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:01:39,865][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:01:40,367][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:01:40,869][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:01:41,371][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:01:41,877][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:01:42,383][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:01:42,885][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:01:43,383][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:01:43,884][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:01:44,385][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:01:44,887][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:01:45,385][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:01:45,887][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:01:46,388][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:01:46,889][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:01:47,390][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:01:47,893][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:01:48,395][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:01:48,897][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:01:49,398][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:01:49,900][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:01:50,402][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:01:50,904][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:01:51,407][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:01:51,915][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:01:52,419][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:01:52,924][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:01:53,428][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:01:53,933][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:01:54,438][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:01:54,942][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:01:55,442][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:01:55,943][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:01:56,442][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:01:56,944][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:01:57,444][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:01:57,944][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:01:58,445][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:01:58,945][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21582 tokens. [2026-03-25 17:02:00,759][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:08 [2026-03-25 17:02:01,487][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:02:01,489][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:02:01,491][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:02:02,109][__main__][INFO] - Iteration 56 took 1m 24s (12.58% Gen, 86.68% Train). Generation: 10s, Training: 1m 13s. Estimated remaining time: 68h 45m 47s. Estimated total time: 70h 12m 36s. Time estimates for 10 more iterations: 14m 2s, 100 more iterations: 2h 20m 25s, 500 more iterations: 11h 42m 6s. [2026-03-25 17:02:02,111][__main__][INFO] - Starting iteration 56. [2026-03-25 17:02:03,228][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:02:03,229][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:02:07,575][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:02:13,725][__main__][INFO] - Number of regex retries in iteration 56: 1 [2026-03-25 17:02:13,725][__main__][INFO] - agents played in iteration 56 are Bob, Alice [2026-03-25 17:02:16,227][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:02:17,292][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:02:18,908][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:02:20,034][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:02:20,536][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:02:21,037][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:02:21,539][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:02:22,040][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:02:22,542][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:02:23,045][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:02:24,147][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:02:25,148][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:02:25,651][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:02:26,153][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:02:26,748][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:02:27,251][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:02:27,756][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:02:28,260][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:02:28,762][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:02:29,263][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:02:29,765][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:02:30,267][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:02:30,768][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:02:31,269][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:02:31,779][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:02:32,283][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:02:32,786][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:02:33,286][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:02:33,787][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:02:34,287][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:02:34,787][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:02:35,287][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:02:35,787][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:02:36,287][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:02:36,789][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:02:37,292][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:02:37,797][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:02:38,300][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:02:38,803][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:02:39,306][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:02:39,808][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:02:40,310][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:02:40,810][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:02:41,314][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:02:41,819][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:02:42,322][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:02:42,826][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:02:43,327][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:02:43,828][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:02:44,327][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:02:44,831][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:02:45,333][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:02:45,834][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:02:46,337][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:02:46,839][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:02:47,341][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:02:47,843][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:02:48,344][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:02:48,849][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:02:49,351][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:02:49,855][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:02:50,358][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:02:50,860][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:02:51,364][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:02:51,865][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:02:52,368][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:02:52,869][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:02:53,370][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:02:53,871][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:02:54,373][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:02:54,875][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:02:55,376][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:02:55,878][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:02:56,380][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:02:56,882][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:02:57,384][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:02:57,885][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:02:58,389][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:02:58,892][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:02:59,396][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:02:59,899][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:03:00,404][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:03:00,906][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:03:01,408][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:03:01,910][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:03:02,411][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:03:02,913][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:03:03,414][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:03:03,918][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:03:04,419][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:03:04,921][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:03:05,422][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:03:05,922][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:03:06,422][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:03:06,922][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:03:07,423][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:03:07,924][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:03:08,424][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:03:08,924][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:03:09,424][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:03:09,923][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:03:10,424][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:03:10,924][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:03:11,426][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:03:11,926][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:03:12,425][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:03:12,926][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:03:13,427][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:03:13,929][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:03:14,431][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:03:14,933][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:03:15,434][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:03:15,936][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:03:16,433][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:03:16,935][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:03:17,437][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:03:17,938][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:03:18,439][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:03:18,940][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:03:19,441][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:03:19,942][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:03:20,443][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:03:20,941][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:03:21,444][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:03:21,946][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:03:22,448][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:03:22,950][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:03:23,451][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:03:23,952][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:03:24,454][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21410 tokens. [2026-03-25 17:03:26,113][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.40%, ΔTime: 00:01:08 [2026-03-25 17:03:26,845][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:03:26,847][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:03:26,849][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:03:27,536][__main__][INFO] - Iteration 57 took 1m 24s (12.45% Gen, 86.73% Train). Generation: 10s, Training: 1m 13s. Estimated remaining time: 68h 47m 10s. Estimated total time: 70h 15m 24s. Time estimates for 10 more iterations: 14m 3s, 100 more iterations: 2h 20m 30s, 500 more iterations: 11h 42m 34s. [2026-03-25 17:03:27,537][__main__][INFO] - Starting iteration 57. [2026-03-25 17:03:28,587][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:03:28,587][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:03:37,817][__main__][INFO] - Number of regex retries in iteration 57: 0 [2026-03-25 17:03:37,818][__main__][INFO] - agents played in iteration 57 are Bob, Alice [2026-03-25 17:03:39,841][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:03:40,906][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:03:42,522][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:03:43,649][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:03:44,401][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:03:44,904][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:03:45,406][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:03:45,907][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:03:46,409][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:03:46,912][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:03:47,414][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:03:47,916][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:03:48,416][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:03:48,918][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:03:49,420][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:03:49,921][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:03:50,420][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:03:50,923][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:03:51,425][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:03:51,927][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:03:52,428][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:03:52,931][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:03:53,432][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:03:53,934][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:03:54,436][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:03:54,937][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:03:55,439][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:03:55,940][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:03:56,442][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:03:56,943][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:03:57,444][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:03:57,945][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:03:58,447][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:03:58,947][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:03:59,449][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:03:59,951][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:04:00,452][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:04:00,953][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:04:01,457][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:04:01,958][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:04:02,460][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:04:02,961][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:04:03,463][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:04:03,964][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:04:04,466][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:04:04,967][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:04:05,471][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:04:05,973][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:04:06,475][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:04:06,977][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:04:07,479][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:04:07,982][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:04:08,483][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:04:08,984][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:04:09,485][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:04:09,985][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:04:10,486][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:04:10,988][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:04:11,491][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:04:11,993][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:04:12,494][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:04:12,997][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:04:13,499][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:04:14,000][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:04:14,502][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:04:15,004][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:04:15,506][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:04:16,007][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:04:16,509][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:04:17,012][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:04:17,514][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:04:18,016][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:04:18,518][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:04:19,020][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:04:19,521][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:04:20,023][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:04:20,524][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:04:21,025][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:04:21,526][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:04:22,027][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:04:22,528][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:04:23,029][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:04:23,531][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:04:24,033][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:04:24,535][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:04:25,037][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:04:25,540][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:04:26,042][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:04:26,544][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:04:27,047][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:04:27,547][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:04:28,048][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:04:28,549][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:04:29,051][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:04:29,552][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:04:30,053][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:04:30,554][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:04:31,056][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:04:31,558][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:04:32,059][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:04:32,561][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:04:33,063][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:04:33,564][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:04:34,065][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:04:34,567][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:04:35,068][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:04:35,570][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:04:36,071][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:04:36,572][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:04:37,075][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:04:37,578][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:04:38,079][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:04:38,581][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:04:39,083][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:04:39,584][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:04:40,084][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:04:40,585][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:04:41,086][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:04:41,588][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:04:42,092][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:04:42,593][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:04:43,095][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:04:43,595][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:04:44,098][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:04:44,597][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:04:45,099][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:04:45,597][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:04:46,101][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:04:46,603][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:04:47,104][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21587 tokens. [2026-03-25 17:04:48,860][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:07 [2026-03-25 17:04:49,590][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:04:49,592][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:04:49,594][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:04:50,215][__main__][INFO] - Iteration 58 took 1m 21s (11.31% Gen, 87.93% Train). Generation: 9s, Training: 1m 11s. Estimated remaining time: 66h 31m 49s. Estimated total time: 68h 1m 26s. Time estimates for 10 more iterations: 13m 36s, 100 more iterations: 2h 16m 2s, 500 more iterations: 11h 20m 14s. [2026-03-25 17:04:50,217][__main__][INFO] - Starting iteration 58. [2026-03-25 17:04:51,330][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:04:51,331][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:04:52,387][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:05:00,904][__main__][INFO] - Number of regex retries in iteration 58: 1 [2026-03-25 17:05:00,905][__main__][INFO] - agents played in iteration 58 are Bob, Alice [2026-03-25 17:05:03,471][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:05:04,540][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:05:06,152][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:05:07,280][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:05:08,031][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:05:08,535][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:05:09,036][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:05:09,536][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:05:10,036][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:05:10,537][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:05:11,532][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:05:12,399][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:05:12,901][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:05:13,403][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:05:13,905][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:05:14,407][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:05:14,910][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:05:15,411][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:05:15,914][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:05:16,742][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:05:17,245][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:05:17,747][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:05:18,250][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:05:18,752][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:05:19,256][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:05:19,758][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:05:20,259][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:05:20,760][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:05:21,263][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:05:21,764][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:05:22,265][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:05:22,766][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:05:23,266][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:05:23,767][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:05:24,268][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:05:24,770][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:05:25,272][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:05:25,773][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:05:26,275][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:05:26,778][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:05:27,280][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:05:27,783][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:05:28,284][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:05:28,786][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:05:29,289][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:05:29,791][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:05:30,293][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:05:30,796][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:05:31,298][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:05:31,800][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:05:32,301][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:05:32,803][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:05:33,304][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:05:33,805][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:05:34,306][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:05:34,808][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:05:35,308][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:05:35,809][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:05:36,310][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:05:36,812][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:05:37,315][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:05:37,816][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:05:38,317][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:05:38,818][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:05:39,320][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:05:39,822][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:05:40,324][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:05:40,822][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:05:41,326][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:05:41,827][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:05:42,326][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:05:42,826][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:05:43,327][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:05:43,828][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:05:44,331][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:05:44,833][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:05:45,338][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:05:45,840][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:05:46,342][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:05:46,844][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:05:47,345][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:05:47,847][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:05:48,349][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:05:48,850][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:05:49,351][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:05:49,853][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:05:50,355][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:05:50,857][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:05:51,359][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:05:51,861][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:05:52,362][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:05:52,863][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:05:53,363][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:05:53,863][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:05:54,364][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:05:54,864][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:05:55,366][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:05:55,866][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:05:56,367][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:05:56,868][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:05:57,369][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:05:57,870][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:05:58,372][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:05:58,874][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:05:59,375][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:05:59,878][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:06:00,381][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:06:00,883][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:06:01,385][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:06:01,886][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:06:02,387][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:06:02,888][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:06:03,390][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:06:03,893][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:06:04,395][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:06:04,896][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:06:05,397][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:06:05,899][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:06:06,400][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:06:06,902][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:06:07,403][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:06:07,904][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:06:08,407][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:06:08,908][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:06:09,409][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:06:09,911][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:06:10,412][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:06:10,913][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:06:11,415][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:06:11,917][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21578 tokens. [2026-03-25 17:06:13,378][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:08 [2026-03-25 17:06:14,111][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:06:14,113][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:06:14,114][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:06:14,756][__main__][INFO] - Iteration 59 took 1m 23s (11.48% Gen, 87.75% Train). Generation: 9s, Training: 1m 13s. Estimated remaining time: 68h 0m 17s. Estimated total time: 69h 31m 18s. Time estimates for 10 more iterations: 13m 54s, 100 more iterations: 2h 19m 2s, 500 more iterations: 11h 35m 13s. [2026-03-25 17:06:14,758][__main__][INFO] - Starting iteration 59. [2026-03-25 17:06:15,848][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:06:15,849][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:06:26,245][__main__][INFO] - Number of regex retries in iteration 59: 0 [2026-03-25 17:06:26,246][__main__][INFO] - agents played in iteration 59 are Bob, Alice [2026-03-25 17:06:28,847][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:06:29,913][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:06:31,532][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:06:32,660][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:06:33,161][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:06:33,662][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:06:34,163][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:06:34,665][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:06:35,164][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:06:35,665][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:06:36,165][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:06:36,665][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:06:37,165][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:06:37,665][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:06:38,165][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:06:38,665][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:06:39,166][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:06:39,666][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:06:40,167][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:06:40,667][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:06:41,169][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:06:41,671][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:06:42,173][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:06:42,674][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:06:43,176][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:06:43,676][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:06:44,177][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:06:44,679][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:06:45,181][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:06:45,684][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:06:46,187][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:06:46,688][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:06:47,189][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:06:47,689][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:06:48,187][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:06:48,690][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:06:49,191][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:06:49,690][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:06:50,191][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:06:50,690][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:06:51,582][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:06:52,436][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:06:53,458][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:06:54,313][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:06:54,816][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:06:55,320][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:06:55,823][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:06:56,326][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:06:56,827][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:06:57,330][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:06:57,832][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:06:58,333][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:06:58,836][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:06:59,338][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:06:59,840][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:07:00,342][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:07:00,844][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:07:01,346][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:07:01,848][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:07:02,350][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:07:02,852][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:07:03,354][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:07:03,856][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:07:04,359][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:07:04,861][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:07:05,363][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:07:05,865][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:07:06,367][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:07:06,869][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:07:07,375][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:07:07,878][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:07:08,380][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:07:08,883][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:07:09,384][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:07:09,888][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:07:10,389][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:07:10,894][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:07:11,399][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:07:11,902][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:07:12,404][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:07:12,906][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:07:13,408][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:07:13,911][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:07:14,411][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:07:14,911][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:07:15,411][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:07:15,912][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:07:16,413][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:07:16,914][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:07:17,415][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:07:17,916][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:07:18,418][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:07:18,918][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:07:19,420][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:07:19,922][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:07:20,423][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:07:20,924][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:07:21,425][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:07:21,925][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:07:22,425][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:07:22,926][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:07:23,424][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:07:23,924][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:07:24,425][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:07:24,925][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:07:25,426][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:07:25,928][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:07:26,430][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:07:26,932][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:07:27,435][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:07:27,937][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:07:28,440][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:07:28,943][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:07:29,446][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:07:29,947][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:07:30,448][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:07:30,948][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:07:31,449][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:07:31,949][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:07:32,450][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:07:32,951][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:07:33,452][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:07:33,952][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:07:34,453][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:07:34,956][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:07:35,457][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:07:35,958][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:07:36,459][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:07:36,960][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:07:37,461][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21658 tokens. [2026-03-25 17:07:38,092][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.27%, ΔTime: 00:01:08 [2026-03-25 17:07:38,821][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:07:38,823][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:07:38,825][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:07:39,448][__main__][INFO] - Iteration 60 took 1m 23s (12.44% Gen, 86.82% Train). Generation: 10s, Training: 1m 12s. Estimated remaining time: 68h 7m 35s. Estimated total time: 69h 40m 1s. Time estimates for 10 more iterations: 13m 56s, 100 more iterations: 2h 19m 20s, 500 more iterations: 11h 36m 40s. [2026-03-25 17:07:39,450][__main__][INFO] - Starting iteration 60. [2026-03-25 17:07:39,851][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:07:39,852][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:07:42,986][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:07:48,461][__main__][INFO] - Number of regex retries in iteration 60: 1 [2026-03-25 17:07:48,462][__main__][INFO] - agents played in iteration 60 are Bob, Alice [2026-03-25 17:07:50,485][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:07:51,552][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:07:53,162][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:07:54,289][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:07:54,789][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:07:55,790][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:07:56,288][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:07:56,789][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:07:57,289][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:07:57,792][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:07:58,293][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:07:58,796][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:07:59,299][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:07:59,802][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:08:00,305][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:08:00,807][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:08:01,308][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:08:01,810][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:08:02,873][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:08:03,376][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:08:03,878][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:08:04,380][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:08:04,882][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:08:05,384][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:08:05,885][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:08:06,385][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:08:07,279][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:08:08,140][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:08:08,644][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:08:09,146][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:08:09,649][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:08:10,152][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:08:10,656][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:08:11,161][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:08:11,664][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:08:12,166][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:08:12,668][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:08:13,169][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:08:13,671][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:08:14,175][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:08:14,677][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:08:15,180][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:08:15,681][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:08:16,183][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:08:16,685][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:08:17,188][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:08:17,689][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:08:18,190][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:08:18,693][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:08:19,198][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:08:19,699][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:08:20,202][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:08:20,704][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:08:21,205][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:08:21,707][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:08:22,208][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:08:22,710][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:08:23,213][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:08:23,714][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:08:24,215][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:08:24,716][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:08:25,218][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:08:25,719][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:08:26,221][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:08:26,723][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:08:27,224][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:08:27,726][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:08:28,228][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:08:28,730][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:08:29,232][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:08:29,734][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:08:30,237][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:08:30,738][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:08:31,241][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:08:31,743][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:08:32,245][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:08:32,748][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:08:33,249][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:08:33,751][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:08:34,253][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:08:34,756][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:08:35,258][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:08:35,759][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:08:36,261][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:08:36,764][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:08:37,266][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:08:37,769][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:08:38,270][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:08:38,772][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:08:39,274][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:08:39,780][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:08:40,282][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:08:40,785][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:08:41,288][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:08:41,790][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:08:42,295][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:08:42,798][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:08:43,303][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:08:43,807][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:08:44,306][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:08:44,808][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:08:45,311][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:08:45,813][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:08:46,316][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:08:46,818][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:08:47,322][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:08:47,825][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:08:48,327][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:08:48,830][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:08:49,332][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:08:49,833][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:08:50,332][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:08:50,837][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:08:51,339][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:08:51,839][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:08:52,341][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:08:52,842][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:08:53,342][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:08:53,843][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:08:54,344][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:08:54,845][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:08:55,346][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:08:55,846][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:08:56,347][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:08:56,848][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:08:57,348][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:08:57,846][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:08:58,348][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:08:58,848][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:08:59,350][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21474 tokens. [2026-03-25 17:09:00,396][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:08 [2026-03-25 17:09:01,134][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:09:01,136][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:09:01,138][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:09:01,769][__main__][INFO] - Iteration 61 took 1m 21s (10.51% Gen, 88.72% Train). Generation: 8s, Training: 1m 12s. Estimated remaining time: 66h 42m 5s. Estimated total time: 68h 15m 53s. Time estimates for 10 more iterations: 13m 39s, 100 more iterations: 2h 16m 31s, 500 more iterations: 11h 22m 38s. [2026-03-25 17:09:01,771][__main__][INFO] - Starting iteration 61. [2026-03-25 17:09:02,867][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:09:02,867][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:09:10,877][__main__][INFO] - Number of regex retries in iteration 61: 0 [2026-03-25 17:09:10,878][__main__][INFO] - agents played in iteration 61 are Bob, Alice [2026-03-25 17:09:13,252][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:09:14,319][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:09:15,933][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:09:17,060][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:09:17,562][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:09:18,065][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:09:18,568][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:09:19,548][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:09:20,051][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:09:20,553][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:09:21,308][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:09:22,162][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:09:22,665][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:09:23,167][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:09:23,669][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:09:24,172][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:09:24,675][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:09:25,179][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:09:25,684][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:09:26,516][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:09:27,019][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:09:27,523][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:09:28,027][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:09:28,531][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:09:29,035][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:09:29,539][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:09:30,041][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:09:30,544][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:09:31,046][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:09:31,548][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:09:32,049][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:09:32,551][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:09:33,053][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:09:33,555][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:09:34,058][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:09:34,561][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:09:35,064][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:09:35,566][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:09:36,069][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:09:36,572][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:09:37,075][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:09:37,578][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:09:38,082][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:09:38,585][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:09:39,089][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:09:39,591][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:09:40,095][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:09:40,598][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:09:41,102][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:09:41,608][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:09:42,111][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:09:42,613][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:09:43,114][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:09:43,618][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:09:44,120][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:09:44,623][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:09:45,126][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:09:45,627][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:09:46,129][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:09:46,629][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:09:47,130][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:09:47,631][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:09:48,132][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:09:48,633][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:09:49,131][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:09:49,635][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:09:50,137][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:09:50,639][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:09:51,141][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:09:51,643][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:09:52,145][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:09:52,646][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:09:53,147][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:09:53,649][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:09:54,151][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:09:54,653][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:09:55,154][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:09:55,658][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:09:56,160][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:09:56,662][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:09:57,164][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:09:57,666][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:09:58,167][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:09:58,670][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:09:59,173][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:09:59,675][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:10:00,179][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:10:00,681][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:10:01,184][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:10:01,686][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:10:02,188][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:10:02,688][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:10:03,189][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:10:03,690][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:10:04,191][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:10:04,692][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:10:05,193][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:10:05,695][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:10:06,197][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:10:06,700][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:10:07,204][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:10:07,707][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:10:08,209][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:10:08,712][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:10:09,214][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:10:09,715][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:10:10,218][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:10:10,720][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:10:11,223][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:10:11,727][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:10:12,229][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:10:12,731][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:10:13,233][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:10:13,737][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:10:14,239][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:10:14,741][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:10:15,244][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:10:15,746][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:10:16,249][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:10:16,751][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:10:17,254][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:10:17,756][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:10:18,258][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:10:18,759][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:10:19,261][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:10:19,762][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:10:20,263][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:10:20,764][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:10:21,264][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:10:21,765][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21722 tokens. [2026-03-25 17:10:23,140][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:08 [2026-03-25 17:10:23,871][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:10:23,873][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:10:23,875][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:10:24,509][__main__][INFO] - Iteration 62 took 1m 21s (9.81% Gen, 89.41% Train). Generation: 8s, Training: 1m 12s. Estimated remaining time: 66h 26m 56s. Estimated total time: 68h 2m 8s. Time estimates for 10 more iterations: 13m 36s, 100 more iterations: 2h 16m 4s, 500 more iterations: 11h 20m 21s. [2026-03-25 17:10:24,511][__main__][INFO] - Starting iteration 62. [2026-03-25 17:10:25,609][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:10:25,610][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:10:29,063][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:10:34,366][__main__][INFO] - Number of regex retries in iteration 62: 1 [2026-03-25 17:10:34,367][__main__][INFO] - agents played in iteration 62 are Bob, Alice [2026-03-25 17:10:36,866][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:10:37,477][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:10:38,673][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:10:39,802][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:10:40,304][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:10:40,806][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:10:41,310][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:10:41,814][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:10:42,317][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:10:42,820][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:10:43,918][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:10:44,909][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:10:45,412][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:10:45,916][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:10:46,419][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:10:46,923][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:10:47,425][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:10:47,927][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:10:48,428][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:10:48,929][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:10:49,429][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:10:49,931][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:10:50,432][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:10:50,933][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:10:51,433][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:10:51,935][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:10:52,437][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:10:52,940][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:10:53,441][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:10:53,942][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:10:54,444][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:10:54,945][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:10:55,446][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:10:55,948][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:10:56,972][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:10:57,965][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:10:58,471][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:10:58,977][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:10:59,483][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:10:59,988][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:11:00,491][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:11:00,997][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:11:01,502][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:11:02,007][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:11:02,511][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:11:03,016][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:11:03,521][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:11:04,025][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:11:04,529][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:11:05,033][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:11:05,536][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:11:06,037][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:11:06,539][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:11:07,042][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:11:07,545][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:11:08,047][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:11:08,550][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:11:09,051][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:11:09,553][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:11:10,054][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:11:10,557][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:11:11,059][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:11:11,563][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:11:12,067][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:11:12,569][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:11:13,070][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:11:13,572][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:11:14,075][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:11:14,577][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:11:15,081][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:11:15,583][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:11:16,085][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:11:16,588][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:11:17,092][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:11:17,595][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:11:18,098][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:11:18,602][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:11:19,106][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:11:19,609][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:11:20,111][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:11:20,613][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:11:21,115][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:11:21,618][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:11:22,120][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:11:22,623][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:11:23,126][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:11:23,629][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:11:24,131][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:11:24,634][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:11:25,137][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:11:25,640][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:11:26,142][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:11:26,645][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:11:27,147][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:11:27,650][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:11:28,152][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:11:28,655][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:11:29,157][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:11:29,663][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:11:30,168][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:11:30,673][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:11:31,177][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:11:31,682][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:11:32,186][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:11:32,692][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:11:33,198][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:11:33,703][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:11:34,207][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:11:34,711][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:11:35,216][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:11:35,721][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:11:36,225][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:11:36,729][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:11:37,234][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:11:37,738][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:11:38,239][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:11:38,741][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:11:39,242][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:11:39,744][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:11:40,245][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:11:40,746][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:11:41,249][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:11:41,753][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:11:42,255][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:11:42,758][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:11:43,260][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:11:43,762][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:11:44,263][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:11:44,765][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:11:45,266][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21659 tokens. [2026-03-25 17:11:46,750][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:09 [2026-03-25 17:11:47,484][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:11:47,486][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:11:47,488][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:11:48,122][__main__][INFO] - Iteration 63 took 1m 22s (10.61% Gen, 88.62% Train). Generation: 8s, Training: 1m 13s. Estimated remaining time: 67h 9m 4s. Estimated total time: 68h 45m 39s. Time estimates for 10 more iterations: 13m 45s, 100 more iterations: 2h 17m 31s, 500 more iterations: 11h 27m 36s. [2026-03-25 17:11:48,124][__main__][INFO] - Starting iteration 63. [2026-03-25 17:11:49,215][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:11:49,216][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:11:58,351][__main__][INFO] - Number of regex retries in iteration 63: 0 [2026-03-25 17:11:58,352][__main__][INFO] - agents played in iteration 63 are Bob, Alice [2026-03-25 17:12:00,470][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:12:01,539][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:12:03,154][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:12:04,283][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:12:04,786][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:12:05,288][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:12:05,791][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:12:06,296][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:12:06,799][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:12:07,303][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:12:07,806][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:12:08,309][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:12:08,813][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:12:09,316][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:12:09,819][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:12:10,323][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:12:10,826][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:12:11,330][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:12:11,832][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:12:12,733][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:12:13,236][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:12:13,738][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:12:14,240][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:12:14,742][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:12:15,244][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:12:15,746][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:12:16,365][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:12:17,227][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:12:17,731][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:12:18,233][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:12:18,739][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:12:19,242][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:12:19,745][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:12:20,250][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:12:20,752][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:12:21,254][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:12:21,758][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:12:22,260][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:12:22,762][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:12:23,264][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:12:23,765][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:12:24,266][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:12:24,768][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:12:25,271][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:12:25,773][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:12:26,276][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:12:26,778][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:12:27,281][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:12:27,783][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:12:28,286][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:12:28,788][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:12:29,291][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:12:29,794][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:12:30,298][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:12:30,801][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:12:31,303][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:12:31,805][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:12:32,308][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:12:32,811][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:12:33,781][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:12:34,285][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:12:34,790][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:12:35,293][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:12:36,389][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:12:36,894][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:12:37,398][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:12:37,901][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:12:38,404][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:12:38,907][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:12:39,410][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:12:39,912][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:12:40,414][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:12:40,917][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:12:41,419][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:12:41,924][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:12:42,426][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:12:42,928][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:12:43,429][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:12:43,931][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:12:44,433][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:12:44,936][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:12:45,438][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:12:45,939][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:12:46,441][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:12:46,943][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:12:47,445][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:12:47,946][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:12:48,448][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:12:48,950][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:12:49,451][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:12:49,953][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:12:50,457][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:12:50,960][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:12:51,462][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:12:51,965][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:12:52,466][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:12:52,968][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:12:53,471][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:12:53,971][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:12:54,469][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:12:54,970][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:12:55,471][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:12:55,972][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:12:56,473][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:12:56,975][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:12:57,476][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:12:57,979][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:12:58,481][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:12:58,983][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:12:59,484][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:12:59,986][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:13:00,487][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:13:00,988][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:13:01,490][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:13:01,991][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:13:02,492][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:13:02,994][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:13:03,495][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:13:03,997][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:13:04,500][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:13:05,003][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:13:05,505][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:13:06,009][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:13:06,512][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:13:07,016][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:13:07,520][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:13:08,023][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:13:08,528][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:13:09,030][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:13:09,534][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21668 tokens. [2026-03-25 17:13:11,248][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.28%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:09 [2026-03-25 17:13:11,979][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:13:11,981][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:13:11,983][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:13:12,781][__main__][INFO] - Iteration 64 took 1m 23s (10.93% Gen, 88.11% Train). Generation: 9s, Training: 1m 13s. Estimated remaining time: 68h 0m 18s. Estimated total time: 69h 38m 18s. Time estimates for 10 more iterations: 13m 55s, 100 more iterations: 2h 19m 16s, 500 more iterations: 11h 36m 23s. [2026-03-25 17:13:12,783][__main__][INFO] - Starting iteration 64. [2026-03-25 17:13:14,452][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:13:14,453][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:13:23,623][__main__][INFO] - Number of regex retries in iteration 64: 0 [2026-03-25 17:13:23,624][__main__][INFO] - agents played in iteration 64 are Bob, Alice [2026-03-25 17:13:25,830][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:13:26,895][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:13:28,509][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:13:29,636][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:13:30,139][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:13:30,642][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:13:31,144][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:13:31,648][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:13:32,151][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:13:32,653][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:13:33,156][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:13:33,659][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:13:34,160][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:13:34,663][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:13:35,164][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:13:35,666][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:13:36,168][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:13:36,671][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:13:37,172][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:13:37,673][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:13:38,176][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:13:38,679][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:13:39,181][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:13:39,682][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:13:40,184][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:13:40,685][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:13:41,185][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:13:41,685][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:13:42,186][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:13:42,686][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:13:43,183][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:13:43,682][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:13:44,181][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:13:44,681][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:13:45,224][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:13:46,079][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:13:46,583][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:13:47,698][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:13:48,203][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:13:48,708][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:13:49,213][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:13:49,717][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:13:50,219][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:13:50,721][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:13:51,224][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:13:51,727][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:13:52,229][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:13:52,730][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:13:53,233][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:13:53,732][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:13:54,235][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:13:54,737][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:13:55,239][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:13:55,740][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:13:56,240][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:13:56,742][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:13:57,244][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:13:57,745][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:13:58,246][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:13:58,748][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:13:59,250][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:13:59,753][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:14:00,255][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:14:00,757][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:14:01,259][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:14:01,761][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:14:02,264][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:14:02,766][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:14:03,269][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:14:03,769][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:14:04,270][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:14:04,771][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:14:05,272][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:14:05,773][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:14:06,274][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:14:06,775][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:14:07,275][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:14:07,777][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:14:08,278][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:14:08,779][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:14:09,280][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:14:09,781][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:14:10,280][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:14:10,781][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:14:11,282][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:14:11,784][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:14:12,283][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:14:12,784][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:14:13,284][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:14:13,784][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:14:14,282][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:14:14,779][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:14:15,276][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:14:15,776][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:14:16,274][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:14:16,772][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:14:17,270][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:14:17,767][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:14:18,271][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:14:18,778][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:14:19,282][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:14:19,786][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:14:20,290][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:14:20,795][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:14:21,298][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:14:21,803][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:14:22,306][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:14:22,807][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:14:23,309][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:14:23,810][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:14:24,312][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:14:24,813][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:14:25,315][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:14:25,817][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:14:26,318][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:14:26,820][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:14:27,321][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:14:27,823][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:14:28,324][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:14:28,825][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:14:29,326][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:14:29,827][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:14:30,327][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:14:30,828][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:14:31,328][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:14:31,829][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:14:32,329][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:14:32,830][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:14:33,330][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:14:33,830][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21629 tokens. [2026-03-25 17:14:34,843][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:07 [2026-03-25 17:14:35,568][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:14:35,570][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:14:35,571][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:14:36,190][__main__][INFO] - Iteration 65 took 1m 21s (11.22% Gen, 88.02% Train). Generation: 9s, Training: 1m 11s. Estimated remaining time: 66h 27m 33s. Estimated total time: 68h 6m 56s. Time estimates for 10 more iterations: 13m 37s, 100 more iterations: 2h 16m 13s, 500 more iterations: 11h 21m 9s. [2026-03-25 17:14:36,192][__main__][INFO] - Starting iteration 65. [2026-03-25 17:14:37,318][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:14:37,318][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:14:45,642][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:14:46,399][__main__][INFO] - Number of regex retries in iteration 65: 1 [2026-03-25 17:14:46,400][__main__][INFO] - agents played in iteration 65 are Bob, Alice [2026-03-25 17:14:48,856][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:14:49,641][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:14:51,253][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:14:53,003][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:14:54,004][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:14:54,507][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:14:55,010][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:14:55,512][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:14:56,013][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:14:56,517][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:14:57,500][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:14:58,356][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:14:58,860][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:14:59,364][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:14:59,866][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:15:00,369][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:15:00,872][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:15:01,376][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:15:01,884][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:15:02,725][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:15:03,592][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:15:04,096][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:15:04,602][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:15:05,325][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:15:05,829][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:15:06,333][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:15:06,833][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:15:07,337][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:15:07,840][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:15:08,343][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:15:08,847][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:15:09,350][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:15:09,853][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:15:10,351][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:15:10,854][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:15:11,359][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:15:11,862][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:15:12,364][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:15:12,866][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:15:13,368][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:15:13,870][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:15:14,372][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:15:14,874][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:15:15,377][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:15:15,879][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:15:16,382][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:15:16,884][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:15:17,386][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:15:17,889][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:15:18,391][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:15:18,893][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:15:19,397][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:15:19,899][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:15:20,402][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:15:20,906][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:15:21,408][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:15:21,909][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:15:22,412][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:15:22,915][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:15:23,420][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:15:23,924][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:15:24,426][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:15:24,930][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:15:25,433][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:15:25,937][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:15:26,440][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:15:26,943][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:15:27,445][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:15:27,946][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:15:28,448][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:15:28,950][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:15:29,453][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:15:29,954][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:15:30,457][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:15:30,960][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:15:31,464][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:15:31,967][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:15:32,470][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:15:32,972][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:15:33,478][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:15:33,982][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:15:34,485][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:15:34,989][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:15:35,493][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:15:36,000][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:15:36,505][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:15:37,011][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:15:37,517][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:15:38,020][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:15:38,526][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:15:39,029][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:15:39,532][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:15:40,035][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:15:40,538][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:15:41,042][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:15:41,547][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:15:42,052][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:15:42,555][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:15:43,056][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:15:43,559][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:15:44,060][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:15:44,563][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:15:45,065][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:15:45,566][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:15:46,067][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:15:46,569][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:15:47,072][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:15:47,574][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:15:48,077][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:15:48,580][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:15:49,083][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:15:49,586][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:15:50,085][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:15:50,588][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:15:51,090][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:15:51,592][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:15:52,095][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:15:52,599][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:15:53,101][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:15:53,604][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:15:54,106][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:15:54,608][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:15:55,112][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:15:55,616][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:15:56,120][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:15:56,624][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:15:57,127][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:15:57,630][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:15:58,134][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:15:58,637][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21593 tokens. [2026-03-25 17:16:00,201][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:10 [2026-03-25 17:16:00,933][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:16:00,936][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:16:00,937][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:16:01,568][__main__][INFO] - Iteration 66 took 1m 24s (10.78% Gen, 88.47% Train). Generation: 9s, Training: 1m 14s. Estimated remaining time: 68h 31m 42s. Estimated total time: 70h 12m 31s. Time estimates for 10 more iterations: 14m 2s, 100 more iterations: 2h 20m 25s, 500 more iterations: 11h 42m 5s. [2026-03-25 17:16:01,570][__main__][INFO] - Starting iteration 66. [2026-03-25 17:16:02,671][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:16:02,671][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:16:13,107][__main__][INFO] - Number of regex retries in iteration 66: 0 [2026-03-25 17:16:13,107][__main__][INFO] - agents played in iteration 66 are Bob, Alice [2026-03-25 17:16:15,680][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:16:16,746][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:16:18,358][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:16:20,104][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:16:21,106][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:16:21,609][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:16:22,111][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:16:22,616][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:16:23,119][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:16:23,622][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:16:24,607][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:16:25,465][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:16:25,969][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:16:26,472][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:16:26,976][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:16:27,479][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:16:27,983][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:16:28,486][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:16:28,993][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:16:29,831][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:16:30,335][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:16:30,838][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:16:31,340][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:16:31,842][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:16:32,345][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:16:32,847][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:16:33,349][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:16:33,850][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:16:34,902][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:16:35,404][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:16:35,906][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:16:36,409][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:16:36,911][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:16:37,414][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:16:37,915][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:16:38,417][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:16:38,918][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:16:39,420][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:16:39,922][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:16:40,424][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:16:40,925][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:16:41,430][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:16:41,934][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:16:42,438][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:16:42,940][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:16:43,619][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:16:44,121][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:16:44,625][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:16:45,127][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:16:45,630][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:16:46,132][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:16:46,637][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:16:47,138][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:16:47,641][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:16:48,144][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:16:48,647][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:16:49,149][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:16:49,652][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:16:50,155][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:16:50,657][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:16:51,160][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:16:51,662][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:16:52,165][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:16:53,200][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:16:53,703][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:16:54,206][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:16:54,707][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:16:55,209][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:16:55,711][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:16:56,216][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:16:56,719][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:16:57,221][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:16:57,723][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:16:58,225][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:16:58,727][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:16:59,230][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:16:59,733][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:17:00,235][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:17:00,737][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:17:01,240][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:17:01,744][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:17:02,247][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:17:02,780][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:17:03,283][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:17:03,786][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:17:04,290][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:17:04,792][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:17:05,295][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:17:05,800][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:17:06,303][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:17:06,807][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:17:07,309][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:17:07,811][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:17:08,312][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:17:08,810][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:17:09,312][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:17:09,814][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:17:10,315][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:17:10,817][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:17:11,318][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:17:11,821][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:17:12,323][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:17:12,824][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:17:13,325][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:17:13,827][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:17:14,328][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:17:14,830][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:17:15,333][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:17:15,836][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:17:16,338][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:17:16,841][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:17:17,343][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:17:17,845][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:17:18,348][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:17:18,850][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:17:19,352][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:17:19,854][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:17:20,357][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:17:20,860][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:17:21,362][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:17:21,865][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:17:22,368][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:17:22,869][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:17:23,371][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:17:23,874][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:17:24,376][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:17:24,878][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:17:25,381][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:17:25,882][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:17:26,384][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21591 tokens. [2026-03-25 17:17:28,187][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:11 [2026-03-25 17:17:28,917][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:17:28,919][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:17:28,921][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:17:29,646][__main__][INFO] - Iteration 67 took 1m 26s (12.00% Gen, 87.17% Train). Generation: 10s, Training: 1m 15s. Estimated remaining time: 70h 46m 32s. Estimated total time: 72h 28m 48s. Time estimates for 10 more iterations: 14m 29s, 100 more iterations: 2h 24m 57s, 500 more iterations: 12h 4m 48s. [2026-03-25 17:17:29,648][__main__][INFO] - Starting iteration 67. [2026-03-25 17:17:30,678][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:17:30,679][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:17:33,245][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:17:38,789][__main__][INFO] - Number of regex retries in iteration 67: 1 [2026-03-25 17:17:38,790][__main__][INFO] - agents played in iteration 67 are Bob, Alice [2026-03-25 17:17:41,040][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:17:42,105][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:17:43,721][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:17:44,850][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:17:45,352][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:17:45,856][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:17:46,359][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:17:46,861][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:17:47,364][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:17:47,866][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:17:48,368][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:17:48,871][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:17:49,817][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:17:50,318][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:17:50,820][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:17:51,321][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:17:51,823][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:17:52,325][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:17:52,825][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:17:53,325][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:17:53,825][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:17:54,325][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:17:54,825][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:17:55,325][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:17:55,825][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:17:56,326][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:17:56,827][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:17:57,328][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:17:57,829][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:17:58,330][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:17:58,831][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:17:59,333][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:17:59,834][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:18:00,336][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:18:00,837][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:18:01,338][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:18:01,839][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:18:02,340][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:18:02,841][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:18:03,342][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:18:03,843][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:18:04,344][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:18:04,845][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:18:05,345][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:18:05,846][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:18:06,346][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:18:06,846][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:18:07,346][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:18:07,847][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:18:08,347][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:18:09,130][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:18:09,633][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:18:10,136][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:18:10,639][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:18:11,142][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:18:11,647][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:18:12,151][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:18:12,657][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:18:13,159][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:18:13,661][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:18:14,163][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:18:14,664][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:18:15,165][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:18:15,667][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:18:16,168][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:18:16,670][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:18:17,174][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:18:17,679][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:18:18,184][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:18:18,688][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:18:19,194][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:18:19,699][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:18:20,203][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:18:20,707][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:18:21,210][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:18:21,713][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:18:22,215][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:18:22,718][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:18:23,220][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:18:23,723][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:18:24,227][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:18:24,730][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:18:25,232][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:18:25,733][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:18:26,236][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:18:26,739][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:18:27,240][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:18:27,742][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:18:28,243][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:18:28,745][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:18:29,248][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:18:29,751][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:18:30,255][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:18:30,757][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:18:31,260][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:18:31,762][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:18:32,265][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:18:32,769][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:18:33,271][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:18:33,773][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:18:34,276][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:18:34,779][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:18:35,282][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:18:35,785][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:18:36,287][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:18:36,789][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:18:37,291][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:18:37,795][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:18:38,298][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:18:38,801][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:18:39,303][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:18:39,806][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:18:40,309][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:18:40,812][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:18:41,318][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:18:41,823][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:18:42,327][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:18:42,831][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:18:43,336][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:18:43,840][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:18:44,344][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:18:44,847][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:18:45,349][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:18:45,851][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:18:46,352][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:18:46,853][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:18:47,355][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:18:47,856][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:18:48,359][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:18:48,861][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21733 tokens. [2026-03-25 17:18:50,065][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:07 [2026-03-25 17:18:50,793][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:18:50,795][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:18:50,799][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:18:51,433][__main__][INFO] - Iteration 68 took 1m 20s (10.04% Gen, 89.17% Train). Generation: 8s, Training: 1m 12s. Estimated remaining time: 65h 34m 8s. Estimated total time: 67h 17m 46s. Time estimates for 10 more iterations: 13m 27s, 100 more iterations: 2h 14m 35s, 500 more iterations: 11h 12m 57s. [2026-03-25 17:18:51,435][__main__][INFO] - Starting iteration 68. [2026-03-25 17:18:52,535][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:18:52,536][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:18:56,273][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:18:56,428][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:18:58,231][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:19:00,810][__main__][INFO] - Number of regex retries in iteration 68: 3 [2026-03-25 17:19:00,811][__main__][INFO] - agents played in iteration 68 are Bob, Alice [2026-03-25 17:19:02,918][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:19:03,987][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:19:05,596][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:19:06,726][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:19:07,229][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:19:07,731][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:19:08,234][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:19:08,738][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:19:09,237][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:19:09,953][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:19:10,978][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:19:11,833][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:19:12,336][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:19:12,839][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:19:13,341][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:19:13,843][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:19:14,347][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:19:14,850][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:19:15,351][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:19:15,853][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:19:16,356][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:19:16,858][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:19:17,360][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:19:17,861][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:19:18,363][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:19:18,865][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:19:19,367][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:19:19,870][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:19:20,373][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:19:20,875][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:19:21,378][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:19:21,880][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:19:22,383][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:19:22,887][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:19:23,389][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:19:23,891][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:19:24,394][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:19:24,898][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:19:25,402][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:19:25,905][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:19:26,409][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:19:26,911][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:19:27,414][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:19:27,917][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:19:28,422][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:19:28,925][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:19:29,427][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:19:29,929][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:19:30,432][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:19:30,936][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:19:31,438][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:19:31,940][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:19:32,441][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:19:32,944][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:19:33,446][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:19:33,948][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:19:34,450][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:19:34,951][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:19:35,454][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:19:35,958][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:19:36,461][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:19:36,964][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:19:37,467][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:19:37,969][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:19:38,472][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:19:38,975][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:19:39,478][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:19:39,980][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:19:40,482][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:19:40,985][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:19:41,490][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:19:41,993][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:19:42,496][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:19:42,999][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:19:43,501][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:19:44,005][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:19:44,507][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:19:45,010][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:19:45,512][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:19:46,014][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:19:46,515][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:19:47,017][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:19:47,518][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:19:48,019][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:19:48,520][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:19:49,021][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:19:49,522][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:19:50,023][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:19:50,523][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:19:51,024][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:19:51,525][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:19:52,027][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:19:52,528][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:19:53,029][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:19:53,530][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:19:54,032][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:19:54,533][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:19:55,035][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:19:55,536][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:19:56,037][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:19:56,540][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:19:57,041][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:19:57,543][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:19:58,044][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:19:58,546][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:19:59,047][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:19:59,549][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:20:00,050][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:20:00,552][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:20:01,053][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:20:01,554][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:20:02,055][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:20:02,558][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:20:03,060][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:20:03,558][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:20:04,059][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:20:04,560][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:20:05,061][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:20:05,562][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:20:06,063][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:20:06,564][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:20:07,066][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:20:07,567][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:20:08,067][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:20:08,568][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:20:09,069][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:20:09,571][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:20:10,072][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:20:10,573][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:20:11,074][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21668 tokens. [2026-03-25 17:20:12,800][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:08 [2026-03-25 17:20:13,517][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:20:13,519][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:20:13,521][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:20:14,141][__main__][INFO] - Iteration 69 took 1m 21s (10.14% Gen, 89.10% Train). Generation: 8s, Training: 1m 12s. Estimated remaining time: 66h 15m 18s. Estimated total time: 68h 0m 19s. Time estimates for 10 more iterations: 13m 36s, 100 more iterations: 2h 16m 0s, 500 more iterations: 11h 20m 3s. [2026-03-25 17:20:14,143][__main__][INFO] - Starting iteration 69. [2026-03-25 17:20:15,273][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:20:15,274][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:20:16,310][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:20:16,311][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:20:19,705][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:20:23,375][__main__][INFO] - Number of regex retries in iteration 69: 3 [2026-03-25 17:20:23,376][__main__][INFO] - agents played in iteration 69 are Bob, Alice [2026-03-25 17:20:25,656][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:20:26,724][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:20:28,339][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:20:30,089][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:20:31,086][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:20:31,585][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:20:32,085][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:20:32,585][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:20:33,084][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:20:33,584][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:20:34,576][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:20:35,438][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:20:35,940][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:20:36,441][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:20:36,943][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:20:37,444][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:20:37,946][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:20:38,446][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:20:38,951][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:20:39,792][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:20:40,293][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:20:40,796][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:20:41,299][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:20:41,802][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:20:42,303][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:20:42,804][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:20:43,304][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:20:43,806][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:20:44,308][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:20:44,810][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:20:45,310][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:20:45,811][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:20:46,312][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:20:46,810][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:20:47,308][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:20:47,809][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:20:48,311][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:20:48,812][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:20:49,313][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:20:49,814][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:20:50,316][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:20:50,816][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:20:51,316][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:20:51,814][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:20:52,312][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:20:52,811][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:20:53,312][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:20:53,812][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:20:54,313][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:20:54,814][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:20:55,314][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:20:55,814][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:20:56,316][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:20:56,817][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:20:57,318][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:20:57,819][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:20:58,320][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:20:58,821][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:20:59,322][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:20:59,822][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:21:00,323][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:21:00,821][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:21:01,323][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:21:01,824][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:21:02,324][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:21:02,824][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:21:03,324][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:21:03,823][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:21:04,323][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:21:04,822][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:21:05,321][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:21:05,821][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:21:06,320][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:21:06,821][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:21:07,323][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:21:07,824][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:21:08,324][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:21:08,826][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:21:09,325][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:21:09,826][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:21:10,327][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:21:10,827][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:21:11,331][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:21:11,832][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:21:12,333][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:21:12,834][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:21:13,335][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:21:13,837][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:21:14,337][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:21:14,838][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:21:15,336][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:21:15,836][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:21:16,337][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:21:16,839][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:21:17,339][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:21:17,840][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:21:18,339][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:21:18,841][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:21:19,342][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:21:19,843][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:21:20,345][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:21:20,846][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:21:21,347][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:21:21,849][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:21:22,350][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:21:22,852][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:21:23,354][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:21:23,854][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:21:24,355][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:21:24,856][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:21:25,356][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:21:25,857][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:21:26,358][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:21:26,859][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:21:27,360][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:21:27,861][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:21:28,362][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:21:28,864][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:21:29,365][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:21:29,866][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:21:30,366][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:21:30,867][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:21:31,367][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:21:31,867][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:21:32,368][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:21:32,869][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:21:33,370][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:21:33,870][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:21:34,370][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:21:34,869][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21470 tokens. [2026-03-25 17:21:36,424][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.20%, ΔTime: 00:01:09 [2026-03-25 17:21:37,145][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:21:37,147][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:21:37,149][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:21:37,776][__main__][INFO] - Iteration 70 took 1m 22s (9.82% Gen, 89.42% Train). Generation: 8s, Training: 1m 13s. Estimated remaining time: 66h 58m 45s. Estimated total time: 68h 45m 10s. Time estimates for 10 more iterations: 13m 45s, 100 more iterations: 2h 17m 30s, 500 more iterations: 11h 27m 31s. [2026-03-25 17:21:37,779][__main__][INFO] - Starting iteration 70. [2026-03-25 17:21:38,890][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:21:38,891][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:21:47,087][__main__][INFO] - Number of regex retries in iteration 70: 0 [2026-03-25 17:21:47,087][__main__][INFO] - agents played in iteration 70 are Bob, Alice [2026-03-25 17:21:49,282][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:21:50,346][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:21:51,961][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:21:53,709][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:21:54,707][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:21:55,209][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:21:55,710][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:21:56,211][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:21:56,711][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:21:57,212][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:21:58,198][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:21:59,059][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:21:59,562][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:22:00,064][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:22:00,567][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:22:01,069][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:22:01,571][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:22:02,075][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:22:02,576][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:22:03,078][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:22:03,579][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:22:04,081][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:22:04,582][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:22:05,083][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:22:05,584][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:22:06,085][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:22:06,587][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:22:07,642][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:22:08,144][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:22:08,646][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:22:09,148][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:22:09,651][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:22:10,151][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:22:10,653][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:22:11,157][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:22:11,662][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:22:12,165][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:22:12,667][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:22:13,169][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:22:13,671][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:22:14,174][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:22:14,677][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:22:15,176][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:22:15,678][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:22:16,178][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:22:16,679][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:22:17,179][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:22:17,679][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:22:18,180][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:22:18,681][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:22:19,183][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:22:19,685][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:22:20,188][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:22:20,690][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:22:21,192][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:22:21,694][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:22:22,197][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:22:22,700][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:22:23,202][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:22:23,705][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:22:24,208][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:22:24,710][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:22:25,214][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:22:25,718][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:22:26,222][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:22:26,724][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:22:27,226][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:22:27,727][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:22:28,229][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:22:28,730][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:22:29,232][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:22:29,735][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:22:30,237][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:22:30,738][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:22:31,244][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:22:31,748][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:22:32,250][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:22:32,753][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:22:33,255][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:22:33,760][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:22:34,262][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:22:34,765][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:22:35,267][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:22:35,767][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:22:36,267][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:22:36,768][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:22:37,269][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:22:37,770][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:22:38,270][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:22:38,773][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:22:39,275][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:22:39,779][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:22:40,282][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:22:40,784][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:22:41,288][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:22:41,792][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:22:42,294][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:22:42,798][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:22:43,301][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:22:43,804][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:22:44,307][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:22:44,810][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:22:45,313][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:22:45,816][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:22:46,319][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:22:46,821][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:22:47,323][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:22:47,824][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:22:48,324][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:22:48,826][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:22:49,327][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:22:49,827][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:22:50,328][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:22:50,829][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:22:51,331][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:22:51,834][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:22:52,336][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:22:52,838][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:22:53,341][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:22:53,843][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:22:54,345][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:22:54,848][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:22:55,350][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:22:55,853][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:22:56,354][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:22:56,857][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:22:57,360][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:22:57,862][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:22:58,365][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:22:58,867][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21737 tokens. [2026-03-25 17:22:59,500][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:09 [2026-03-25 17:23:00,225][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:23:00,227][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:23:00,228][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:23:00,850][__main__][INFO] - Iteration 71 took 1m 21s (10.00% Gen, 89.24% Train). Generation: 8s, Training: 1m 13s. Estimated remaining time: 66h 30m 13s. Estimated total time: 68h 18m 1s. Time estimates for 10 more iterations: 13m 39s, 100 more iterations: 2h 16m 36s, 500 more iterations: 11h 23m 0s. [2026-03-25 17:23:00,852][__main__][INFO] - Starting iteration 71. [2026-03-25 17:23:02,475][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:23:02,476][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:23:11,085][__main__][INFO] - Number of regex retries in iteration 71: 0 [2026-03-25 17:23:11,085][__main__][INFO] - agents played in iteration 71 are Bob, Alice [2026-03-25 17:23:12,886][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:23:13,950][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:23:15,565][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:23:16,690][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:23:17,441][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:23:17,943][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:23:18,444][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:23:18,946][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:23:19,447][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:23:19,947][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:23:20,938][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:23:21,440][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:23:21,941][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:23:22,442][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:23:22,943][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:23:23,538][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:23:24,040][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:23:24,541][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:23:25,041][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:23:25,541][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:23:26,041][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:23:26,541][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:23:27,041][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:23:27,542][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:23:28,042][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:23:28,540][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:23:29,041][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:23:29,543][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:23:30,044][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:23:30,545][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:23:31,047][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:23:31,548][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:23:32,049][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:23:32,550][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:23:33,121][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:23:33,981][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:23:34,483][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:23:34,985][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:23:35,487][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:23:35,990][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:23:36,491][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:23:36,994][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:23:37,495][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:23:37,998][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:23:38,500][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:23:39,002][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:23:39,504][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:23:40,006][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:23:40,507][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:23:41,009][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:23:41,511][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:23:42,015][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:23:42,519][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:23:43,023][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:23:43,525][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:23:44,027][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:23:44,529][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:23:45,030][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:23:45,532][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:23:46,035][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:23:46,536][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:23:47,038][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:23:47,541][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:23:48,044][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:23:48,547][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:23:49,050][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:23:49,550][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:23:50,051][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:23:50,552][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:23:51,055][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:23:51,556][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:23:52,057][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:23:52,558][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:23:53,060][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:23:53,562][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:23:54,064][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:23:54,566][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:23:55,067][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:23:55,568][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:23:56,069][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:23:56,572][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:23:57,073][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:23:57,574][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:23:58,074][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:23:58,574][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:23:59,074][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:23:59,576][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:24:00,077][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:24:00,578][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:24:01,078][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:24:01,580][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:24:02,082][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:24:02,583][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:24:03,084][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:24:03,586][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:24:04,087][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:24:04,588][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:24:05,089][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:24:05,591][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:24:06,093][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:24:06,596][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:24:07,099][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:24:07,601][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:24:08,103][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:24:08,606][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:24:09,108][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:24:09,609][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:24:10,112][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:24:10,614][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:24:11,116][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:24:11,620][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:24:12,123][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:24:12,626][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:24:13,128][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:24:13,630][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:24:14,132][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:24:14,637][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:24:15,140][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:24:15,642][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:24:16,145][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:24:16,647][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:24:17,150][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:24:17,653][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:24:18,156][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:24:18,660][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:24:19,163][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:24:19,666][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:24:20,169][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:24:20,672][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:24:21,175][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21696 tokens. [2026-03-25 17:24:22,785][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:08 [2026-03-25 17:24:23,517][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:24:23,519][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:24:23,520][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:24:24,160][__main__][INFO] - Iteration 72 took 1m 21s (10.54% Gen, 88.68% Train). Generation: 8s, Training: 1m 12s. Estimated remaining time: 66h 15m 3s. Estimated total time: 68h 4m 14s. Time estimates for 10 more iterations: 13m 36s, 100 more iterations: 2h 16m 8s, 500 more iterations: 11h 20m 42s. [2026-03-25 17:24:24,162][__main__][INFO] - Starting iteration 72. [2026-03-25 17:24:25,250][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:24:25,251][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:24:26,296][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:24:27,933][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:24:33,099][__main__][INFO] - Number of regex retries in iteration 72: 2 [2026-03-25 17:24:33,099][__main__][INFO] - agents played in iteration 72 are Bob, Alice [2026-03-25 17:24:35,634][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:24:36,697][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:24:38,314][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:24:39,448][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:24:39,950][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:24:40,453][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:24:40,956][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:24:41,460][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:24:41,965][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:24:42,467][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:24:42,967][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:24:43,468][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:24:43,969][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:24:44,470][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:24:44,970][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:24:45,470][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:24:45,970][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:24:46,470][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:24:47,183][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:24:48,040][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:24:48,543][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:24:49,046][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:24:49,548][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:24:50,051][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:24:50,554][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:24:51,056][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:24:51,558][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:24:52,060][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:24:52,562][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:24:53,064][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:24:53,566][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:24:54,068][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:24:54,571][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:24:55,073][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:24:55,574][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:24:56,078][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:24:56,579][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:24:57,081][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:24:57,582][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:24:58,083][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:24:58,584][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:24:59,085][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:24:59,588][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:25:00,090][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:25:00,592][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:25:01,094][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:25:01,597][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:25:02,099][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:25:02,602][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:25:03,105][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:25:03,607][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:25:04,109][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:25:04,611][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:25:05,114][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:25:05,617][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:25:06,119][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:25:06,621][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:25:07,124][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:25:07,628][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:25:08,131][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:25:08,634][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:25:09,137][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:25:09,639][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:25:10,142][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:25:10,645][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:25:11,148][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:25:11,653][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:25:12,155][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:25:12,660][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:25:13,163][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:25:13,665][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:25:14,168][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:25:14,670][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:25:15,174][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:25:15,677][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:25:16,179][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:25:16,681][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:25:17,183][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:25:17,686][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:25:18,187][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:25:18,690][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:25:19,192][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:25:19,695][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:25:20,200][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:25:20,703][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:25:21,207][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:25:21,711][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:25:22,214][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:25:22,717][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:25:23,220][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:25:23,722][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:25:24,225][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:25:24,728][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:25:25,230][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:25:25,732][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:25:26,233][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:25:26,736][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:25:27,239][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:25:27,740][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:25:28,241][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:25:28,742][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:25:29,244][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:25:29,745][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:25:30,246][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:25:30,748][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:25:31,249][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:25:31,749][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:25:32,252][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:25:32,754][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:25:33,258][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:25:33,762][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:25:34,264][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:25:34,766][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:25:35,268][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:25:35,770][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:25:36,272][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:25:36,773][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:25:37,276][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:25:37,778][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:25:38,281][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:25:38,783][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:25:39,285][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:25:39,788][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:25:40,290][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:25:40,793][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:25:41,299][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:25:41,803][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:25:42,307][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:25:42,810][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:25:43,313][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 17:25:44,653][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.36%, ΔTime: 00:01:07 [2026-03-25 17:25:45,383][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:25:45,385][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:25:45,387][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:25:46,008][__main__][INFO] - Iteration 73 took 1m 20s (9.72% Gen, 89.51% Train). Generation: 7s, Training: 1m 12s. Estimated remaining time: 65h 27m 24s. Estimated total time: 67h 17m 56s. Time estimates for 10 more iterations: 13m 27s, 100 more iterations: 2h 14m 35s, 500 more iterations: 11h 12m 59s. [2026-03-25 17:25:46,010][__main__][INFO] - Starting iteration 73. [2026-03-25 17:25:47,131][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:25:47,132][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:25:48,182][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:25:51,690][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:25:55,079][__main__][INFO] - Number of regex retries in iteration 73: 2 [2026-03-25 17:25:55,080][__main__][INFO] - agents played in iteration 73 are Bob, Alice [2026-03-25 17:25:57,521][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:25:58,583][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:26:00,197][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:26:01,332][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:26:01,834][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:26:02,337][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:26:02,839][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:26:03,342][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:26:03,845][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:26:04,347][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:26:04,849][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:26:05,350][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:26:05,852][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:26:06,354][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:26:06,856][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:26:07,357][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:26:07,858][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:26:08,359][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:26:09,040][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:26:09,541][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:26:10,043][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:26:10,545][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:26:11,047][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:26:11,550][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:26:12,052][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:26:12,555][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:26:13,055][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:26:13,559][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:26:14,060][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:26:14,562][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:26:15,063][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:26:15,564][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:26:16,065][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:26:16,567][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:26:17,067][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:26:17,569][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:26:18,070][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:26:18,572][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:26:19,073][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:26:19,576][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:26:20,079][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:26:20,581][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:26:21,105][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:26:21,607][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:26:22,110][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:26:22,613][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:26:23,116][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:26:23,620][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:26:24,123][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:26:24,626][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:26:25,128][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:26:25,630][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:26:26,131][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:26:26,633][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:26:27,136][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:26:27,638][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:26:28,141][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:26:28,642][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:26:29,145][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:26:29,647][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:26:30,150][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:26:30,653][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:26:31,156][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:26:31,660][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:26:32,163][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:26:32,666][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:26:33,290][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:26:33,795][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:26:34,299][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:26:34,803][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:26:35,307][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:26:35,811][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:26:36,315][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:26:36,819][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:26:37,322][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:26:37,825][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:26:38,327][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:26:38,830][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:26:39,332][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:26:39,835][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:26:40,338][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:26:40,841][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:26:41,346][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:26:41,849][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:26:42,352][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:26:42,854][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:26:43,357][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:26:43,860][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:26:44,363][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:26:44,866][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:26:45,368][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:26:45,869][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:26:46,371][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:26:46,873][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:26:47,377][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:26:47,879][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:26:48,381][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:26:48,882][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:26:49,384][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:26:49,887][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:26:50,389][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:26:50,893][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:26:51,395][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:26:51,899][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:26:52,402][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:26:52,905][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:26:53,409][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:26:53,912][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:26:54,415][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:26:54,918][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:26:55,421][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:26:55,924][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:26:56,428][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:26:56,931][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:26:57,432][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:26:57,934][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:26:58,437][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:26:58,940][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:26:59,442][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:26:59,944][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:27:00,446][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:27:00,948][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:27:01,451][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:27:01,954][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:27:02,457][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:27:02,961][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:27:03,464][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:27:03,967][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:27:04,470][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:27:04,973][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 17:27:06,542][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:07 [2026-03-25 17:27:07,273][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:27:07,275][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:27:07,276][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:27:07,908][__main__][INFO] - Iteration 74 took 1m 20s (9.84% Gen, 89.38% Train). Generation: 7s, Training: 1m 12s. Estimated remaining time: 65h 26m 58s. Estimated total time: 67h 18m 53s. Time estimates for 10 more iterations: 13m 27s, 100 more iterations: 2h 14m 37s, 500 more iterations: 11h 13m 8s. [2026-03-25 17:27:07,910][__main__][INFO] - Starting iteration 74. [2026-03-25 17:27:09,010][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:27:09,011][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:27:10,046][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:27:16,338][__main__][INFO] - Number of regex retries in iteration 74: 1 [2026-03-25 17:27:16,339][__main__][INFO] - agents played in iteration 74 are Bob, Alice [2026-03-25 17:27:18,806][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:27:19,593][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:27:21,209][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:27:21,732][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:27:22,234][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:27:22,737][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:27:23,239][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:27:23,741][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:27:24,243][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:27:24,745][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:27:25,712][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:27:26,568][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:27:27,071][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:27:27,574][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:27:28,076][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:27:28,580][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:27:29,082][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:27:29,585][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:27:30,086][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:27:30,587][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:27:31,087][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:27:31,588][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:27:32,088][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:27:32,589][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:27:33,089][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:27:33,590][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:27:34,091][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:27:34,593][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:27:35,094][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:27:35,600][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:27:36,101][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:27:36,604][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:27:37,105][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:27:37,607][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:27:38,109][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:27:38,610][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:27:39,112][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:27:39,614][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:27:40,116][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:27:40,617][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:27:41,119][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:27:41,623][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:27:42,125][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:27:42,627][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:27:43,129][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:27:43,630][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:27:44,133][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:27:44,635][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:27:45,138][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:27:45,640][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:27:46,141][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:27:46,644][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:27:47,145][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:27:47,647][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:27:48,148][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:27:48,650][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:27:49,151][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:27:49,652][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:27:50,154][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:27:50,655][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:27:51,156][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:27:51,658][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:27:52,160][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:27:52,660][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:27:53,160][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:27:53,661][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:27:54,162][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:27:54,664][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:27:55,167][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:27:55,668][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:27:56,169][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:27:56,671][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:27:57,173][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:27:57,674][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:27:58,176][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:27:58,681][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:27:59,184][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:27:59,686][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:28:00,189][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:28:00,691][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:28:01,194][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:28:01,697][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:28:02,199][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:28:02,699][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:28:03,200][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:28:03,700][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:28:04,200][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:28:04,701][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:28:05,201][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:28:05,702][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:28:06,203][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:28:06,704][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:28:07,206][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:28:07,707][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:28:08,209][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:28:08,710][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:28:09,211][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:28:09,713][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:28:10,214][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:28:10,716][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:28:11,217][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:28:11,721][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:28:12,225][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:28:12,727][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:28:13,229][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:28:13,730][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:28:14,232][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:28:14,734][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:28:15,237][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:28:15,739][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:28:16,240][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:28:16,743][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:28:17,245][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:28:17,747][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:28:18,249][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:28:18,750][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:28:19,252][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:28:19,754][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:28:20,254][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:28:20,758][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:28:21,259][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:28:21,760][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:28:22,262][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:28:22,763][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:28:23,264][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:28:23,765][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:28:24,266][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:28:24,767][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:28:25,268][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:28:25,768][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 17:28:27,532][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:07 [2026-03-25 17:28:28,253][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:28:28,255][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:28:28,257][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:28:28,932][__main__][INFO] - Iteration 75 took 1m 19s (9.17% Gen, 89.98% Train). Generation: 7s, Training: 1m 11s. Estimated remaining time: 64h 42m 52s. Estimated total time: 66h 36m 7s. Time estimates for 10 more iterations: 13m 19s, 100 more iterations: 2h 13m 12s, 500 more iterations: 11h 6m 1s. [2026-03-25 17:28:28,934][__main__][INFO] - Starting iteration 75. [2026-03-25 17:28:30,002][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:28:30,002][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:28:37,517][__main__][INFO] - Number of regex retries in iteration 75: 0 [2026-03-25 17:28:37,518][__main__][INFO] - agents played in iteration 75 are Bob, Alice [2026-03-25 17:28:39,520][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:28:40,581][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:28:42,199][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:28:43,328][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:28:43,830][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:28:44,332][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:28:44,834][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:28:45,336][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:28:45,839][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:28:46,340][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:28:46,842][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:28:47,342][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:28:47,843][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:28:48,344][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:28:48,845][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:28:49,345][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:28:49,845][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:28:50,345][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:28:50,845][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:28:51,346][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:28:51,847][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:28:52,347][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:28:52,847][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:28:53,348][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:28:53,849][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:28:54,350][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:28:55,420][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:28:56,275][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:28:56,778][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:28:57,281][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:28:57,783][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:28:58,286][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:28:58,788][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:28:59,290][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:28:59,792][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:29:00,294][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:29:00,797][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:29:01,300][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:29:01,802][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:29:02,304][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:29:02,806][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:29:03,308][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:29:03,810][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:29:04,312][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:29:04,813][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:29:05,315][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:29:05,816][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:29:06,319][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:29:06,821][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:29:07,322][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:29:08,346][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:29:09,338][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:29:09,841][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:29:10,343][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:29:10,845][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:29:11,348][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:29:11,851][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:29:12,355][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:29:12,856][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:29:13,357][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:29:13,859][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:29:14,360][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:29:14,861][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:29:15,362][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:29:15,863][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:29:16,364][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:29:16,865][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:29:17,366][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:29:17,866][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:29:18,367][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:29:18,869][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:29:19,369][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:29:19,870][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:29:20,371][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:29:20,871][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:29:21,371][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:29:21,870][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:29:22,370][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:29:22,870][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:29:23,370][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:29:23,869][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:29:24,368][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:29:24,867][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:29:25,367][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:29:25,867][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:29:26,367][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:29:26,867][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:29:27,367][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:29:27,864][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:29:28,364][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:29:28,866][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:29:29,368][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:29:29,868][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:29:30,370][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:29:30,871][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:29:31,372][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:29:31,874][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:29:32,377][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:29:32,879][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:29:33,381][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:29:33,882][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:29:34,384][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:29:34,885][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:29:35,386][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:29:35,887][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:29:36,389][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:29:36,889][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:29:37,390][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:29:37,890][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:29:38,392][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:29:38,894][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:29:39,395][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:29:39,895][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:29:40,397][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:29:40,900][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:29:41,403][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:29:41,907][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:29:42,410][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:29:42,911][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:29:43,412][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:29:43,913][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:29:44,416][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:29:44,916][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:29:45,417][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:29:45,917][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:29:46,418][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:29:46,920][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:29:47,421][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:29:47,921][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:29:48,423][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21741 tokens. [2026-03-25 17:29:49,410][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:08 [2026-03-25 17:29:50,136][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:29:50,138][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:29:50,140][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:29:50,821][__main__][INFO] - Iteration 76 took 1m 20s (9.30% Gen, 89.86% Train). Generation: 7s, Training: 1m 12s. Estimated remaining time: 65h 26m 23s. Estimated total time: 67h 21m 0s. Time estimates for 10 more iterations: 13m 28s, 100 more iterations: 2h 14m 42s, 500 more iterations: 11h 13m 30s. [2026-03-25 17:29:50,823][__main__][INFO] - Starting iteration 76. [2026-03-25 17:29:51,883][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:29:51,883][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:29:59,461][__main__][INFO] - Number of regex retries in iteration 76: 0 [2026-03-25 17:29:59,462][__main__][INFO] - agents played in iteration 76 are Bob, Alice [2026-03-25 17:30:01,403][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:30:02,462][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:30:04,080][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:30:05,208][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:30:05,710][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:30:06,212][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:30:06,713][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:30:07,214][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:30:07,715][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:30:08,217][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:30:08,719][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:30:09,220][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:30:09,722][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:30:10,223][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:30:10,724][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:30:11,227][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:30:11,728][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:30:12,229][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:30:12,730][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:30:13,231][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:30:13,733][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:30:14,235][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:30:14,741][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:30:15,243][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:30:15,745][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:30:16,248][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:30:16,747][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:30:17,249][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:30:17,749][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:30:18,249][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:30:18,749][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:30:19,249][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:30:19,753][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:30:20,253][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:30:20,756][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:30:21,257][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:30:21,759][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:30:22,261][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:30:22,761][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:30:23,263][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:30:23,764][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:30:24,265][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:30:24,766][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:30:25,267][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:30:25,768][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:30:26,269][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:30:26,771][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:30:27,272][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:30:27,772][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:30:28,273][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:30:28,777][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:30:29,280][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:30:29,782][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:30:30,284][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:30:30,787][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:30:31,289][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:30:31,790][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:30:32,291][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:30:32,796][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:30:33,299][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:30:33,802][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:30:34,305][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:30:34,807][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:30:35,310][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:30:35,811][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:30:36,312][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:30:36,812][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:30:37,313][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:30:37,815][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:30:38,317][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:30:38,818][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:30:39,319][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:30:39,822][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:30:40,323][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:30:40,825][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:30:41,329][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:30:41,832][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:30:42,333][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:30:42,835][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:30:43,336][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:30:43,838][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:30:44,340][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:30:44,841][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:30:45,343][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:30:45,844][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:30:46,345][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:30:46,846][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:30:47,347][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:30:47,848][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:30:48,349][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:30:48,847][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:30:49,346][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:30:49,845][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:30:50,345][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:30:50,844][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:30:51,343][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:30:51,842][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:30:52,341][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:30:52,843][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:30:53,344][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:30:53,845][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:30:54,344][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:30:54,846][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:30:55,347][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:30:55,847][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:30:56,348][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:30:56,848][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:30:57,348][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:30:57,850][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:30:58,350][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:30:58,852][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:30:59,351][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:30:59,852][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:31:00,353][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:31:00,853][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:31:01,355][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:31:01,856][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:31:02,357][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:31:02,859][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:31:03,360][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:31:03,861][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:31:04,363][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:31:04,864][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:31:05,366][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:31:05,867][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:31:06,368][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:31:06,869][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:31:07,372][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:31:07,873][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:31:08,375][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21686 tokens. [2026-03-25 17:31:08,998][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:06 [2026-03-25 17:31:09,727][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:31:09,729][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:31:09,730][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:31:10,360][__main__][INFO] - Iteration 77 took 1m 18s (9.66% Gen, 89.54% Train). Generation: 7s, Training: 1m 10s. Estimated remaining time: 63h 27m 57s. Estimated total time: 65h 23m 54s. Time estimates for 10 more iterations: 13m 4s, 100 more iterations: 2h 10m 47s, 500 more iterations: 10h 53m 59s. [2026-03-25 17:31:10,362][__main__][INFO] - Starting iteration 77. [2026-03-25 17:31:10,766][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:31:10,766][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:31:11,904][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:31:12,460][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:31:17,502][__main__][INFO] - Number of regex retries in iteration 77: 2 [2026-03-25 17:31:17,503][__main__][INFO] - agents played in iteration 77 are Bob, Alice [2026-03-25 17:31:18,500][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:31:19,091][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:31:19,548][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:31:20,054][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:31:20,555][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:31:21,056][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:31:21,560][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:31:22,061][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:31:22,562][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:31:23,064][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:31:23,566][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:31:24,067][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:31:24,567][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:31:25,068][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:31:25,570][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:31:26,071][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:31:26,572][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:31:27,073][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:31:27,573][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:31:28,074][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:31:28,575][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:31:29,078][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:31:29,579][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:31:30,081][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:31:30,582][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:31:31,084][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:31:31,585][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:31:32,085][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:31:32,587][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:31:33,087][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:31:33,588][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:31:34,089][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:31:34,589][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:31:35,091][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:31:35,593][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:31:36,095][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:31:36,600][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:31:37,103][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:31:37,606][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:31:38,109][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:31:38,611][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:31:39,113][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:31:39,615][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:31:40,117][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:31:40,620][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:31:41,122][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:31:41,623][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:31:42,124][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:31:42,626][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:31:43,127][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:31:43,629][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:31:44,131][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:31:44,633][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:31:45,134][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:31:45,637][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:31:46,140][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:31:46,642][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:31:47,144][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:31:47,645][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:31:48,147][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:31:48,649][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:31:49,151][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:31:49,653][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:31:50,155][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:31:50,657][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:31:51,159][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:31:51,662][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:31:52,163][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:31:52,665][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:31:53,167][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:31:53,668][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:31:54,169][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:31:54,670][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:31:55,172][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:31:55,674][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:31:56,176][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:31:56,680][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:31:57,182][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:31:57,685][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:31:58,188][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:31:58,689][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:31:59,192][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:31:59,693][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:32:00,195][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:32:00,698][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:32:01,201][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:32:01,703][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:32:02,206][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:32:02,708][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:32:03,210][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:32:03,711][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:32:04,213][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:32:04,714][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:32:05,215][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:32:05,715][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:32:06,218][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:32:06,719][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:32:07,222][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:32:07,725][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:32:08,227][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:32:08,729][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:32:09,231][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:32:09,733][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:32:10,235][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:32:10,738][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:32:11,243][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:32:11,745][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:32:12,246][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:32:12,747][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:32:13,248][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:32:13,749][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:32:14,250][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:32:14,750][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:32:15,251][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:32:15,753][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:32:16,254][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:32:16,756][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:32:17,259][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:32:17,761][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:32:18,264][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:32:18,766][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:32:19,268][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:32:19,771][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:32:20,273][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:32:20,776][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:32:21,279][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:32:21,781][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:32:22,284][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:32:22,786][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:32:23,288][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 17:32:23,919][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:04 [2026-03-25 17:32:24,651][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:32:24,653][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:32:24,655][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:32:25,290][__main__][INFO] - Iteration 78 took 1m 14s (9.04% Gen, 90.11% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 60h 9m 3s. Estimated total time: 62h 6m 15s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 12s, 500 more iterations: 10h 21m 2s. [2026-03-25 17:32:25,293][__main__][INFO] - Starting iteration 78. [2026-03-25 17:32:25,693][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:32:25,693][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:32:31,703][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:32:33,024][__main__][INFO] - Number of regex retries in iteration 78: 1 [2026-03-25 17:32:33,025][__main__][INFO] - agents played in iteration 78 are Bob, Alice [2026-03-25 17:32:34,067][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:32:34,947][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:32:35,408][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:32:35,915][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:32:36,419][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:32:36,923][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:32:37,428][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:32:37,931][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:32:38,434][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:32:38,938][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:32:39,440][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:32:39,943][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:32:40,446][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:32:40,949][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:32:41,454][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:32:41,958][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:32:42,461][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:32:42,964][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:32:43,468][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:32:43,971][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:32:44,473][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:32:44,975][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:32:45,478][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:32:45,980][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:32:46,482][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:32:46,985][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:32:47,490][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:32:47,993][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:32:48,500][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:32:49,004][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:32:49,509][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:32:50,012][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:32:50,515][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:32:51,020][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:32:51,523][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:32:52,027][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:32:52,530][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:32:53,032][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:32:53,536][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:32:54,040][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:32:54,543][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:32:55,045][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:32:55,549][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:32:56,052][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:32:56,556][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:32:57,060][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:32:57,564][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:32:58,067][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:32:58,570][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:32:59,073][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:32:59,578][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:33:00,081][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:33:00,585][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:33:01,087][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:33:01,590][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:33:02,093][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:33:02,598][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:33:03,101][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:33:03,605][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:33:04,108][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:33:04,611][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:33:05,114][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:33:05,617][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:33:06,120][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:33:06,623][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:33:07,127][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:33:07,631][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:33:08,134][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:33:08,637][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:33:09,140][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:33:09,643][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:33:10,146][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:33:10,649][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:33:11,154][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:33:11,659][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:33:12,162][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:33:12,664][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:33:13,168][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:33:13,671][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:33:14,173][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:33:14,677][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:33:15,180][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:33:15,683][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:33:16,186][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:33:16,687][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:33:17,190][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:33:17,692][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:33:18,194][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:33:18,698][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:33:19,202][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:33:19,706][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:33:20,209][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:33:20,713][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:33:21,217][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:33:21,720][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:33:22,224][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:33:22,728][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:33:23,231][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:33:23,734][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:33:24,237][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:33:24,740][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:33:25,242][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:33:25,745][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:33:26,248][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:33:26,751][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:33:27,255][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:33:27,759][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:33:28,263][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:33:28,767][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:33:29,271][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:33:29,774][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:33:30,278][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:33:30,782][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:33:31,285][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:33:31,789][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:33:32,292][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:33:32,797][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:33:33,301][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:33:33,805][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:33:34,309][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:33:34,813][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:33:35,316][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:33:35,817][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:33:36,320][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:33:36,820][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:33:37,319][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:33:37,820][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:33:38,324][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:33:38,823][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:33:39,323][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21640 tokens. [2026-03-25 17:33:39,963][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 17:33:40,695][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:33:40,697][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:33:40,699][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:33:41,337][__main__][INFO] - Iteration 79 took 1m 15s (9.69% Gen, 89.46% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 61h 3m 46s. Estimated total time: 63h 2m 14s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 4s, 500 more iterations: 10h 30m 22s. [2026-03-25 17:33:41,339][__main__][INFO] - Starting iteration 79. [2026-03-25 17:33:41,740][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:33:41,740][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:33:48,708][__main__][INFO] - Number of regex retries in iteration 79: 0 [2026-03-25 17:33:48,708][__main__][INFO] - agents played in iteration 79 are Bob, Alice [2026-03-25 17:33:49,674][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:33:50,274][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:33:50,734][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:33:51,242][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:33:51,746][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:33:52,249][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:33:52,751][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:33:53,254][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:33:53,758][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:33:54,260][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:33:54,764][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:33:55,267][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:33:55,769][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:33:56,272][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:33:56,775][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:33:57,277][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:33:57,781][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:33:58,284][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:33:58,789][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:33:59,293][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:33:59,795][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:34:00,298][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:34:00,801][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:34:01,306][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:34:01,809][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:34:02,313][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:34:02,814][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:34:03,315][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:34:03,816][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:34:04,318][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:34:04,819][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:34:05,321][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:34:05,822][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:34:06,322][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:34:06,827][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:34:07,332][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:34:07,835][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:34:08,338][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:34:08,842][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:34:09,345][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:34:09,848][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:34:10,352][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:34:10,856][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:34:11,361][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:34:11,866][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:34:12,369][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:34:12,873][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:34:13,376][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:34:13,881][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:34:14,386][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:34:14,888][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:34:15,391][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:34:15,892][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:34:16,394][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:34:16,897][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:34:17,401][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:34:17,903][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:34:18,405][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:34:18,907][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:34:19,409][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:34:19,912][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:34:20,415][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:34:20,918][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:34:21,421][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:34:21,925][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:34:22,428][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:34:22,931][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:34:23,434][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:34:23,937][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:34:24,440][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:34:24,943][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:34:25,446][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:34:25,949][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:34:26,452][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:34:26,954][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:34:27,457][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:34:27,960][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:34:28,463][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:34:28,965][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:34:29,468][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:34:29,977][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:34:30,481][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:34:30,986][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:34:31,490][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:34:31,992][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:34:32,496][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:34:33,000][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:34:33,503][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:34:34,006][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:34:34,509][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:34:35,010][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:34:35,511][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:34:36,012][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:34:36,513][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:34:37,015][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:34:37,516][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:34:38,017][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:34:38,518][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:34:39,023][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:34:39,526][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:34:40,030][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:34:40,533][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:34:41,037][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:34:41,543][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:34:42,046][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:34:42,550][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:34:43,052][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:34:43,554][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:34:44,056][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:34:44,561][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:34:45,065][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:34:45,569][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:34:46,072][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:34:46,574][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:34:47,078][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:34:47,580][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:34:48,082][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:34:48,585][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:34:49,086][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:34:49,588][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:34:50,090][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:34:50,593][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:34:51,096][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:34:51,598][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:34:52,102][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:34:52,606][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:34:53,109][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:34:53,613][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:34:54,115][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:34:54,618][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21650 tokens. [2026-03-25 17:34:55,269][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 17:34:56,004][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:34:56,007][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:34:56,009][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:34:56,646][__main__][INFO] - Iteration 80 took 1m 14s (9.30% Gen, 89.85% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 60h 25m 36s. Estimated total time: 62h 25m 19s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 50s, 500 more iterations: 10h 24m 13s. [2026-03-25 17:34:56,648][__main__][INFO] - Starting iteration 80. [2026-03-25 17:34:57,053][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:34:57,054][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:35:03,859][__main__][INFO] - Number of regex retries in iteration 80: 0 [2026-03-25 17:35:03,860][__main__][INFO] - agents played in iteration 80 are Bob, Alice [2026-03-25 17:35:04,854][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:35:05,448][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:35:05,908][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:35:06,415][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:35:06,918][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:35:07,420][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:35:07,921][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:35:08,429][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:35:08,931][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:35:09,434][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:35:09,936][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:35:10,437][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:35:10,937][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:35:11,442][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:35:11,944][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:35:12,445][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:35:12,946][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:35:13,446][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:35:13,947][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:35:14,448][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:35:14,949][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:35:15,451][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:35:15,952][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:35:16,454][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:35:16,955][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:35:17,457][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:35:17,961][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:35:18,465][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:35:18,968][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:35:19,470][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:35:19,974][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:35:20,478][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:35:20,981][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:35:21,484][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:35:21,986][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:35:22,488][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:35:22,990][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:35:23,493][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:35:23,995][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:35:24,498][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:35:25,001][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:35:25,505][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:35:26,007][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:35:26,510][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:35:27,012][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:35:27,514][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:35:28,015][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:35:28,519][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:35:29,021][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:35:29,523][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:35:30,025][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:35:30,527][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:35:31,028][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:35:31,528][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:35:32,029][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:35:32,530][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:35:33,031][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:35:33,532][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:35:34,033][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:35:34,533][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:35:35,036][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:35:35,538][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:35:36,040][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:35:36,542][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:35:37,046][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:35:37,549][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:35:38,050][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:35:38,552][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:35:39,054][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:35:39,555][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:35:40,056][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:35:40,559][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:35:41,061][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:35:41,566][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:35:42,067][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:35:42,568][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:35:43,068][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:35:43,570][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:35:44,071][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:35:44,573][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:35:45,073][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:35:45,580][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:35:46,084][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:35:46,588][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:35:47,092][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:35:47,594][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:35:48,099][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:35:48,603][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:35:49,106][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:35:49,609][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:35:50,112][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:35:50,614][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:35:51,116][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:35:51,621][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:35:52,123][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:35:52,626][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:35:53,129][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:35:53,631][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:35:54,133][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:35:54,636][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:35:55,138][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:35:55,640][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:35:56,141][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:35:56,644][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:35:57,147][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:35:57,648][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:35:58,151][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:35:58,652][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:35:59,155][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:35:59,656][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:36:00,160][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:36:00,661][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:36:01,163][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:36:01,665][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:36:02,165][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:36:02,666][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:36:03,167][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:36:03,667][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:36:04,168][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:36:04,669][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:36:05,170][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:36:05,670][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:36:06,171][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:36:06,672][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:36:07,175][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:36:07,676][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:36:08,179][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:36:08,681][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:36:09,183][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:36:09,685][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 17:36:10,335][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-25 17:36:11,090][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:36:11,093][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:36:11,094][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:36:11,775][__main__][INFO] - Iteration 81 took 1m 14s (9.11% Gen, 89.98% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 60h 15m 10s. Estimated total time: 62h 16m 9s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 32s, 500 more iterations: 10h 22m 41s. [2026-03-25 17:36:11,777][__main__][INFO] - Starting iteration 81. [2026-03-25 17:36:12,179][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:36:12,180][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:36:13,415][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:36:19,376][__main__][INFO] - Number of regex retries in iteration 81: 1 [2026-03-25 17:36:19,377][__main__][INFO] - agents played in iteration 81 are Bob, Alice [2026-03-25 17:36:20,303][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:36:20,901][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:36:21,361][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:36:21,868][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:36:22,371][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:36:22,872][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:36:23,375][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:36:23,877][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:36:24,384][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:36:24,888][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:36:25,393][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:36:25,897][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:36:26,401][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:36:26,905][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:36:27,409][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:36:27,913][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:36:28,417][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:36:28,921][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:36:29,423][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:36:29,926][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:36:30,427][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:36:30,930][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:36:31,432][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:36:31,934][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:36:32,436][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:36:32,939][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:36:33,441][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:36:33,944][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:36:34,447][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:36:34,950][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:36:35,452][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:36:35,955][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:36:36,458][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:36:36,960][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:36:37,463][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:36:37,967][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:36:38,472][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:36:38,975][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:36:39,481][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:36:39,985][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:36:40,489][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:36:40,993][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:36:41,498][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:36:42,002][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:36:42,506][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:36:43,011][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:36:43,514][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:36:44,017][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:36:44,519][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:36:45,021][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:36:45,524][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:36:46,025][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:36:46,527][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:36:47,029][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:36:47,530][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:36:48,033][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:36:48,534][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:36:49,037][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:36:49,539][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:36:50,041][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:36:50,543][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:36:51,045][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:36:51,546][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:36:52,049][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:36:52,550][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:36:53,053][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:36:53,554][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:36:54,059][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:36:54,561][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:36:55,064][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:36:55,566][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:36:56,068][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:36:56,569][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:36:57,070][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:36:57,573][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:36:58,077][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:36:58,580][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:36:59,084][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:36:59,588][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:37:00,090][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:37:00,594][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:37:01,099][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:37:01,602][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:37:02,106][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:37:02,609][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:37:03,112][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:37:03,614][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:37:04,116][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:37:04,617][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:37:05,120][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:37:05,622][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:37:06,123][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:37:06,625][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:37:07,128][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:37:07,630][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:37:08,130][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:37:08,632][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:37:09,133][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:37:09,636][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:37:10,141][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:37:10,646][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:37:11,149][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:37:11,653][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:37:12,156][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:37:12,659][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:37:13,162][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:37:13,664][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:37:14,166][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:37:14,668][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:37:15,170][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:37:15,672][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:37:16,173][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:37:16,677][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:37:17,180][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:37:17,681][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:37:18,184][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:37:18,683][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:37:19,186][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:37:19,688][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:37:20,190][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:37:20,689][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:37:21,191][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:37:21,693][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:37:22,194][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:37:22,699][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:37:23,200][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:37:23,702][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:37:24,204][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:37:24,706][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:37:25,209][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21711 tokens. [2026-03-25 17:37:25,846][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-25 17:37:26,577][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:37:26,579][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:37:26,580][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:37:27,316][__main__][INFO] - Iteration 82 took 1m 15s (9.58% Gen, 89.44% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 60h 34m 37s. Estimated total time: 62h 36m 51s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 13s, 500 more iterations: 10h 26m 8s. [2026-03-25 17:37:27,318][__main__][INFO] - Starting iteration 82. [2026-03-25 17:37:27,718][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:37:27,718][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:37:34,970][__main__][INFO] - Number of regex retries in iteration 82: 0 [2026-03-25 17:37:34,971][__main__][INFO] - agents played in iteration 82 are Bob, Alice [2026-03-25 17:37:35,895][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:37:36,495][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:37:36,955][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:37:37,463][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:37:37,967][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:37:38,469][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:37:38,971][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:37:39,474][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:37:39,978][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:37:40,480][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:37:40,982][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:37:41,486][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:37:41,988][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:37:42,489][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:37:42,990][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:37:43,491][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:37:43,994][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:37:44,496][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:37:44,999][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:37:45,501][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:37:46,003][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:37:46,506][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:37:47,008][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:37:47,510][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:37:48,011][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:37:48,513][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:37:49,015][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:37:49,519][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:37:50,022][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:37:50,524][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:37:51,026][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:37:51,528][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:37:52,030][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:37:52,532][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:37:53,034][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:37:53,535][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:37:54,036][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:37:54,539][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:37:55,042][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:37:55,544][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:37:56,045][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:37:56,547][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:37:57,049][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:37:57,550][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:37:58,051][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:37:58,553][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:37:59,055][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:37:59,557][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:38:00,059][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:38:00,557][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:38:01,059][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:38:01,560][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:38:02,061][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:38:02,562][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:38:03,063][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:38:03,564][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:38:04,065][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:38:04,566][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:38:05,067][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:38:05,569][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:38:06,070][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:38:06,571][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:38:07,072][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:38:07,574][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:38:08,075][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:38:08,576][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:38:09,080][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:38:09,583][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:38:10,086][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:38:10,589][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:38:11,092][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:38:11,596][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:38:12,099][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:38:12,603][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:38:13,106][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:38:13,608][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:38:14,110][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:38:14,611][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:38:15,113][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:38:15,615][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:38:16,117][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:38:16,619][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:38:17,120][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:38:17,622][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:38:18,124][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:38:18,626][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:38:19,128][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:38:19,629][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:38:20,131][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:38:20,632][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:38:21,133][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:38:21,635][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:38:22,138][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:38:22,640][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:38:23,142][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:38:23,644][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:38:24,146][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:38:24,648][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:38:25,150][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:38:25,652][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:38:26,154][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:38:26,656][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:38:27,160][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:38:27,662][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:38:28,164][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:38:28,666][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:38:29,168][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:38:29,670][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:38:30,171][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:38:30,672][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:38:31,174][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:38:31,675][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:38:32,177][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:38:32,680][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:38:33,182][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:38:33,683][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:38:34,185][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:38:34,687][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:38:35,188][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:38:35,689][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:38:36,191][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:38:36,693][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:38:37,196][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:38:37,699][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:38:38,202][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:38:38,704][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:38:39,206][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:38:39,709][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:38:40,211][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:38:40,712][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21698 tokens. [2026-03-25 17:38:41,347][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:04 [2026-03-25 17:38:42,079][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:38:42,081][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:38:42,083][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:38:42,763][__main__][INFO] - Iteration 83 took 1m 15s (9.66% Gen, 89.43% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 60h 28m 46s. Estimated total time: 62h 32m 16s. Time estimates for 10 more iterations: 12m 30s, 100 more iterations: 2h 5m 4s, 500 more iterations: 10h 25m 22s. [2026-03-25 17:38:42,765][__main__][INFO] - Starting iteration 83. [2026-03-25 17:38:43,164][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:38:43,164][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:38:44,743][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:38:47,420][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:38:49,119][__main__][INFO] - Number of regex retries in iteration 83: 2 [2026-03-25 17:38:49,119][__main__][INFO] - agents played in iteration 83 are Bob, Alice [2026-03-25 17:38:50,080][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:38:50,673][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:38:51,131][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:38:51,637][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:38:52,141][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:38:52,643][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:38:53,145][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:38:53,647][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:38:54,149][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:38:54,650][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:38:55,151][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:38:55,652][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:38:56,153][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:38:56,655][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:38:57,156][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:38:57,657][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:38:58,159][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:38:58,661][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:38:59,162][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:38:59,663][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:39:00,164][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:39:00,665][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:39:01,165][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:39:01,666][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:39:02,167][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:39:02,669][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:39:03,169][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:39:03,670][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:39:04,171][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:39:04,673][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:39:05,175][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:39:05,677][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:39:06,178][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:39:06,680][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:39:07,181][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:39:07,682][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:39:08,183][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:39:08,684][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:39:09,185][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:39:09,686][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:39:10,187][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:39:10,687][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:39:11,190][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:39:11,694][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:39:12,198][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:39:12,700][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:39:13,203][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:39:13,707][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:39:14,209][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:39:14,711][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:39:15,215][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:39:15,718][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:39:16,220][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:39:16,722][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:39:17,225][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:39:17,727][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:39:18,229][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:39:18,731][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:39:19,232][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:39:19,733][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:39:20,234][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:39:20,735][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:39:21,236][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:39:21,737][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:39:22,238][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:39:22,740][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:39:23,241][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:39:23,741][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:39:24,241][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:39:24,741][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:39:25,241][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:39:25,741][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:39:26,241][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:39:26,741][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:39:27,242][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:39:27,744][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:39:28,245][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:39:28,746][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:39:29,248][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:39:29,748][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:39:30,249][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:39:30,750][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:39:31,252][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:39:31,752][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:39:32,252][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:39:32,754][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:39:33,254][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:39:33,755][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:39:34,255][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:39:34,756][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:39:35,256][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:39:35,758][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:39:36,259][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:39:36,760][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:39:37,261][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:39:37,763][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:39:38,263][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:39:38,764][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:39:39,264][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:39:39,764][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:39:40,264][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:39:40,764][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:39:41,266][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:39:41,767][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:39:42,267][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:39:42,768][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:39:43,269][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:39:43,770][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:39:44,271][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:39:44,771][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:39:45,271][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:39:45,772][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:39:46,274][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:39:46,775][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:39:47,277][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:39:47,780][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:39:48,281][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:39:48,783][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:39:49,285][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:39:49,787][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:39:50,289][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:39:50,791][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:39:51,293][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:39:51,796][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:39:52,300][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:39:52,801][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:39:53,304][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:39:53,808][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:39:54,308][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:39:54,809][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21760 tokens. [2026-03-25 17:39:55,439][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-25 17:39:56,167][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:39:56,169][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:39:56,170][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:39:56,794][__main__][INFO] - Iteration 84 took 1m 13s (8.09% Gen, 91.06% Train). Generation: 5s, Training: 1m 7s. Estimated remaining time: 59h 16m 49s. Estimated total time: 61h 21m 32s. Time estimates for 10 more iterations: 12m 16s, 100 more iterations: 2h 2m 43s, 500 more iterations: 10h 13m 35s. [2026-03-25 17:39:56,796][__main__][INFO] - Starting iteration 84. [2026-03-25 17:39:57,198][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:39:57,199][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:39:59,712][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:40:04,754][__main__][INFO] - Number of regex retries in iteration 84: 1 [2026-03-25 17:40:04,755][__main__][INFO] - agents played in iteration 84 are Bob, Alice [2026-03-25 17:40:05,702][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:40:06,299][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:40:06,756][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:40:07,263][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:40:07,764][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:40:08,265][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:40:08,766][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:40:09,267][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:40:09,767][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:40:10,268][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:40:10,768][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:40:11,271][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:40:11,774][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:40:12,277][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:40:12,779][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:40:13,280][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:40:13,782][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:40:14,284][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:40:14,785][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:40:15,287][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:40:15,788][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:40:16,289][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:40:16,790][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:40:17,292][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:40:17,793][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:40:18,295][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:40:18,795][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:40:19,299][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:40:19,800][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:40:20,301][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:40:20,803][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:40:21,304][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:40:21,805][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:40:22,307][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:40:22,811][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:40:23,314][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:40:23,817][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:40:24,319][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:40:24,821][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:40:25,323][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:40:25,825][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:40:26,327][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:40:26,828][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:40:27,329][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:40:27,830][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:40:28,330][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:40:28,831][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:40:29,331][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:40:29,832][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:40:30,332][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:40:30,833][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:40:31,334][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:40:31,835][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:40:32,337][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:40:32,838][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:40:33,340][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:40:33,841][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:40:34,342][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:40:34,842][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:40:35,343][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:40:35,844][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:40:36,344][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:40:36,845][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:40:37,345][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:40:37,846][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:40:38,346][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:40:38,847][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:40:39,348][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:40:39,850][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:40:40,351][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:40:40,851][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:40:41,353][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:40:41,855][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:40:42,356][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:40:42,857][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:40:43,358][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:40:43,859][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:40:44,362][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:40:44,863][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:40:45,365][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:40:45,866][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:40:46,368][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:40:46,868][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:40:47,376][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:40:47,879][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:40:48,382][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:40:48,884][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:40:49,387][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:40:49,889][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:40:50,390][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:40:50,893][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:40:51,394][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:40:51,895][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:40:52,397][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:40:52,901][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:40:53,404][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:40:53,906][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:40:54,408][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:40:54,910][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:40:55,412][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:40:55,914][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:40:56,417][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:40:56,919][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:40:57,421][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:40:57,923][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:40:58,425][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:40:58,926][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:40:59,427][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:40:59,928][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:41:00,429][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:41:00,928][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:41:01,428][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:41:01,928][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:41:02,428][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:41:02,929][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:41:03,430][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:41:03,931][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:41:04,430][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:41:04,931][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:41:05,432][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:41:05,932][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:41:06,433][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:41:06,934][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:41:07,434][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:41:07,933][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:41:08,433][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:41:08,934][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:41:09,435][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:41:09,935][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:41:10,435][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21671 tokens. [2026-03-25 17:41:11,087][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-25 17:41:11,809][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:41:11,811][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:41:11,813][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:41:12,485][__main__][INFO] - Iteration 85 took 1m 15s (10.04% Gen, 89.07% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 60h 38m 24s. Estimated total time: 62h 44m 23s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 28s, 500 more iterations: 10h 27m 23s. [2026-03-25 17:41:12,488][__main__][INFO] - Starting iteration 85. [2026-03-25 17:41:12,891][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:41:12,891][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:41:19,391][__main__][INFO] - Number of regex retries in iteration 85: 0 [2026-03-25 17:41:19,392][__main__][INFO] - agents played in iteration 85 are Bob, Alice [2026-03-25 17:41:20,377][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:41:20,970][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:41:21,428][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:41:21,935][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:41:22,436][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:41:22,939][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:41:23,441][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:41:23,942][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:41:24,443][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:41:24,944][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:41:25,448][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:41:25,955][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:41:26,457][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:41:26,960][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:41:27,463][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:41:27,965][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:41:28,468][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:41:28,970][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:41:29,471][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:41:29,971][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:41:30,472][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:41:30,973][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:41:31,474][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:41:31,974][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:41:32,475][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:41:32,974][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:41:33,476][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:41:33,976][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:41:34,479][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:41:34,980][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:41:35,481][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:41:35,982][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:41:36,483][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:41:36,984][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:41:37,485][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:41:37,987][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:41:38,489][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:41:38,989][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:41:39,489][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:41:39,989][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:41:40,491][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:41:40,992][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:41:41,496][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:41:41,997][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:41:42,498][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:41:42,999][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:41:43,500][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:41:44,001][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:41:44,503][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:41:45,004][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:41:45,505][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:41:46,005][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:41:46,506][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:41:47,007][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:41:47,508][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:41:48,009][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:41:48,511][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:41:49,012][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:41:49,509][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:41:50,008][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:41:50,507][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:41:51,007][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:41:51,506][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:41:52,005][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:41:52,504][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:41:53,004][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:41:53,506][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:41:54,008][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:41:54,509][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:41:55,013][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:41:55,516][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:41:56,017][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:41:56,519][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:41:57,020][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:41:57,523][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:41:58,025][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:41:58,528][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:41:59,030][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:41:59,531][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:42:00,033][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:42:00,536][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:42:01,038][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:42:01,538][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:42:02,040][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:42:02,546][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:42:03,048][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:42:03,549][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:42:04,050][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:42:04,551][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:42:05,051][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:42:05,552][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:42:06,053][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:42:06,555][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:42:07,056][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:42:07,557][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:42:08,058][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:42:08,560][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:42:09,061][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:42:09,562][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:42:10,063][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:42:10,564][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:42:11,065][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:42:11,567][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:42:12,068][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:42:12,568][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:42:13,070][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:42:13,570][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:42:14,071][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:42:14,571][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:42:15,072][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:42:15,572][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:42:16,072][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:42:16,573][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:42:17,073][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:42:17,574][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:42:18,074][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:42:18,575][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:42:19,076][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:42:19,578][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:42:20,078][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:42:20,577][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:42:21,078][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:42:21,576][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:42:22,074][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:42:22,573][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:42:23,071][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:42:23,570][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:42:24,069][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:42:24,568][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:42:25,066][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 17:42:25,713][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.13%, Current % of VRAM taken: 60.49%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 17:42:26,435][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:42:26,437][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:42:26,438][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:42:27,131][__main__][INFO] - Iteration 86 took 1m 14s (8.76% Gen, 90.31% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 44m 49s. Estimated total time: 61h 52m 2s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 44s, 500 more iterations: 10h 18m 40s. [2026-03-25 17:42:27,133][__main__][INFO] - Starting iteration 86. [2026-03-25 17:42:27,535][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:42:27,536][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:42:34,049][__main__][INFO] - Number of regex retries in iteration 86: 0 [2026-03-25 17:42:34,050][__main__][INFO] - agents played in iteration 86 are Bob, Alice [2026-03-25 17:42:35,053][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:42:35,644][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:42:36,102][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:42:36,606][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:42:37,106][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:42:37,605][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:42:38,105][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:42:38,604][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:42:39,103][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:42:39,602][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:42:40,107][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:42:40,610][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:42:41,125][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:42:41,632][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:42:42,136][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:42:42,641][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:42:43,145][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:42:43,649][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:42:44,152][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:42:44,654][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:42:45,156][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:42:45,660][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:42:46,162][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:42:46,664][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:42:47,166][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:42:47,668][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:42:48,169][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:42:48,670][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:42:49,171][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:42:49,673][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:42:50,175][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:42:50,676][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:42:51,178][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:42:51,680][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:42:52,182][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:42:52,683][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:42:53,184][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:42:53,684][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:42:54,185][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:42:54,685][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:42:55,186][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:42:55,687][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:42:56,190][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:42:56,691][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:42:57,191][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:42:57,691][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:42:58,192][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:42:58,692][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:42:59,192][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:42:59,693][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:43:00,197][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:43:00,700][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:43:01,203][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:43:01,706][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:43:02,210][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:43:02,712][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:43:03,214][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:43:03,716][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:43:04,220][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:43:04,722][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:43:05,225][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:43:05,727][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:43:06,229][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:43:06,731][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:43:07,235][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:43:07,738][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:43:08,238][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:43:08,736][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:43:09,235][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:43:09,732][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:43:10,230][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:43:10,729][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:43:11,228][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:43:11,728][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:43:12,232][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:43:12,736][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:43:13,238][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:43:13,743][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:43:14,248][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:43:14,751][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:43:15,255][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:43:15,759][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:43:16,262][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:43:16,764][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:43:17,266][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:43:17,768][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:43:18,270][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:43:18,771][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:43:19,274][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:43:19,777][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:43:20,279][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:43:20,781][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:43:21,283][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:43:21,785][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:43:22,286][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:43:22,789][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:43:23,290][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:43:23,792][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:43:24,291][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:43:24,790][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:43:25,290][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:43:25,790][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:43:26,291][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:43:26,790][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:43:27,290][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:43:27,790][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:43:28,289][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:43:28,788][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:43:29,289][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:43:29,790][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:43:30,290][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:43:30,789][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:43:31,289][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:43:31,789][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:43:32,292][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:43:32,796][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:43:33,300][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:43:33,803][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:43:34,306][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:43:34,809][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:43:35,312][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:43:35,815][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:43:36,317][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:43:36,819][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:43:37,321][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:43:37,823][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:43:38,326][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:43:38,829][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:43:39,331][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:43:39,838][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 17:43:40,485][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.43%, ΔTime: 00:01:04 [2026-03-25 17:43:41,216][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:43:41,218][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:43:41,220][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:43:41,912][__main__][INFO] - Iteration 87 took 1m 14s (8.76% Gen, 90.31% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 50m 25s. Estimated total time: 61h 58m 54s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 57s, 500 more iterations: 10h 19m 49s. [2026-03-25 17:43:41,915][__main__][INFO] - Starting iteration 87. [2026-03-25 17:43:42,315][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:43:42,316][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:43:49,177][__main__][INFO] - Number of regex retries in iteration 87: 0 [2026-03-25 17:43:49,178][__main__][INFO] - agents played in iteration 87 are Bob, Alice [2026-03-25 17:43:50,134][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:43:50,726][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:43:51,185][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:43:51,692][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:43:52,194][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:43:52,696][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:43:53,198][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:43:53,702][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:43:54,205][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:43:54,707][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:43:55,208][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:43:55,710][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:43:56,210][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:43:56,712][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:43:57,212][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:43:57,713][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:43:58,216][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:43:58,717][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:43:59,217][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:43:59,718][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:44:00,220][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:44:00,721][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:44:01,222][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:44:01,723][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:44:02,223][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:44:02,724][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:44:03,227][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:44:03,729][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:44:04,231][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:44:04,733][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:44:05,234][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:44:05,734][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:44:06,236][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:44:06,738][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:44:07,240][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:44:07,741][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:44:08,242][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:44:08,743][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:44:09,244][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:44:09,746][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:44:10,247][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:44:10,748][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:44:11,258][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:44:11,762][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:44:12,264][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:44:12,766][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:44:13,267][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:44:13,769][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:44:14,270][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:44:14,770][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:44:15,272][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:44:15,773][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:44:16,274][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:44:16,775][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:44:17,277][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:44:17,779][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:44:18,283][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:44:18,785][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:44:19,287][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:44:19,788][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:44:20,289][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:44:20,790][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:44:21,293][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:44:21,795][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:44:22,297][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:44:22,798][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:44:23,301][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:44:23,803][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:44:24,306][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:44:24,809][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:44:25,311][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:44:25,812][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:44:26,314][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:44:26,816][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:44:27,317][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:44:27,819][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:44:28,320][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:44:28,820][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:44:29,322][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:44:29,823][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:44:30,324][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:44:30,825][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:44:31,325][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:44:31,826][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:44:32,327][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:44:32,827][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:44:33,328][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:44:33,828][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:44:34,329][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:44:34,829][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:44:35,330][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:44:35,831][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:44:36,332][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:44:36,834][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:44:37,336][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:44:37,837][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:44:38,338][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:44:38,839][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:44:39,342][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:44:39,844][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:44:40,345][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:44:40,847][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:44:41,351][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:44:41,853][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:44:42,353][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:44:42,854][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:44:43,355][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:44:43,856][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:44:44,357][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:44:44,858][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:44:45,358][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:44:45,860][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:44:46,361][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:44:46,862][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:44:47,362][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:44:47,864][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:44:48,369][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:44:48,870][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:44:49,371][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:44:49,873][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:44:50,374][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:44:50,875][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:44:51,376][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:44:51,881][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:44:52,382][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:44:52,883][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:44:53,385][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:44:53,886][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:44:54,387][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:44:54,888][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21746 tokens. [2026-03-25 17:44:55,538][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:04 [2026-03-25 17:44:56,287][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:44:56,289][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:44:56,291][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:44:56,985][__main__][INFO] - Iteration 88 took 1m 14s (9.19% Gen, 89.88% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 60h 3m 46s. Estimated total time: 62h 13m 30s. Time estimates for 10 more iterations: 12m 26s, 100 more iterations: 2h 4m 27s, 500 more iterations: 10h 22m 15s. [2026-03-25 17:44:56,987][__main__][INFO] - Starting iteration 88. [2026-03-25 17:44:57,389][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:44:57,390][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:45:03,729][__main__][INFO] - Number of regex retries in iteration 88: 0 [2026-03-25 17:45:03,730][__main__][INFO] - agents played in iteration 88 are Bob, Alice [2026-03-25 17:45:04,708][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:45:05,297][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:45:05,756][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:45:06,262][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:45:06,765][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:45:07,266][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:45:07,769][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:45:08,271][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:45:08,773][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:45:09,275][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:45:09,782][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:45:10,286][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:45:10,790][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:45:11,297][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:45:11,802][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:45:12,306][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:45:12,810][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:45:13,315][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:45:13,816][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:45:14,317][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:45:14,818][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:45:15,319][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:45:15,821][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:45:16,322][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:45:16,823][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:45:17,325][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:45:17,826][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:45:18,327][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:45:18,828][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:45:19,329][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:45:19,830][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:45:20,331][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:45:20,832][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:45:21,332][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:45:21,835][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:45:22,338][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:45:22,842][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:45:23,344][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:45:23,847][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:45:24,349][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:45:24,851][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:45:25,354][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:45:25,855][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:45:26,362][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:45:26,863][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:45:27,366][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:45:27,868][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:45:28,370][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:45:28,871][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:45:29,371][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:45:29,871][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:45:30,370][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:45:30,871][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:45:31,371][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:45:31,872][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:45:32,372][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:45:32,874][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:45:33,376][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:45:33,878][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:45:34,379][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:45:34,880][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:45:35,422][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:45:35,924][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:45:36,426][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:45:36,928][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:45:37,429][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:45:37,931][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:45:38,434][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:45:38,938][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:45:39,440][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:45:39,942][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:45:40,445][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:45:40,949][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:45:41,453][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:45:41,958][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:45:42,463][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:45:42,968][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:45:43,473][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:45:43,979][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:45:44,485][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:45:44,990][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:45:45,495][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:45:46,000][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:45:46,502][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:45:47,003][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:45:47,505][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:45:48,007][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:45:48,512][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:45:49,014][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:45:49,516][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:45:50,017][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:45:50,519][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:45:51,021][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:45:51,523][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:45:52,025][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:45:52,527][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:45:53,028][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:45:53,531][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:45:54,033][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:45:54,537][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:45:55,041][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:45:55,544][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:45:56,047][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:45:56,551][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:45:57,054][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:45:57,558][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:45:58,061][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:45:58,563][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:45:59,065][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:45:59,569][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:46:00,072][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:46:00,575][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:46:01,076][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:46:01,581][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:46:02,082][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:46:02,584][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:46:03,086][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:46:03,588][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:46:04,090][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:46:04,590][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:46:05,091][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:46:05,592][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:46:06,094][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:46:06,595][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:46:07,099][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:46:07,603][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:46:08,104][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:46:08,606][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:46:09,109][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:46:09,610][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21663 tokens. [2026-03-25 17:46:10,259][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.53%, ΔTime: 00:01:04 [2026-03-25 17:46:10,995][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:46:10,998][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:46:10,999][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:46:11,704][__main__][INFO] - Iteration 89 took 1m 14s (8.53% Gen, 90.52% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 44m 48s. Estimated total time: 61h 55m 46s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 51s, 500 more iterations: 10h 19m 17s. [2026-03-25 17:46:11,707][__main__][INFO] - Starting iteration 89. [2026-03-25 17:46:12,113][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:46:12,114][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:46:19,248][__main__][INFO] - Number of regex retries in iteration 89: 0 [2026-03-25 17:46:19,249][__main__][INFO] - agents played in iteration 89 are Bob, Alice [2026-03-25 17:46:20,249][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:46:20,845][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:46:21,306][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:46:21,813][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:46:22,318][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:46:22,822][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:46:23,327][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:46:23,831][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:46:24,334][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:46:24,839][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:46:25,342][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:46:25,845][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:46:26,346][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:46:26,850][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:46:27,353][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:46:27,857][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:46:28,360][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:46:28,861][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:46:29,364][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:46:29,866][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:46:30,369][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:46:30,871][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:46:31,374][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:46:31,876][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:46:32,379][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:46:32,883][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:46:33,386][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:46:33,889][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:46:34,392][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:46:34,894][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:46:35,397][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:46:35,902][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:46:36,406][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:46:36,909][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:46:37,411][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:46:37,912][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:46:38,415][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:46:38,917][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:46:39,419][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:46:39,920][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:46:40,422][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:46:40,923][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:46:41,428][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:46:41,931][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:46:42,435][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:46:42,938][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:46:43,441][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:46:43,944][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:46:44,447][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:46:44,951][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:46:45,453][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:46:45,995][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:46:46,549][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:46:47,052][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:46:47,554][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:46:48,056][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:46:48,559][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:46:49,063][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:46:49,567][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:46:50,070][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:46:50,573][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:46:51,077][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:46:51,583][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:46:52,088][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:46:52,591][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:46:53,095][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:46:53,600][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:46:54,099][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:46:54,602][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:46:55,107][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:46:55,611][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:46:56,114][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:46:56,620][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:46:57,123][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:46:57,627][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:46:58,130][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:46:58,632][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:46:59,133][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:46:59,638][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:47:00,141][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:47:00,644][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:47:01,146][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:47:01,650][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:47:02,152][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:47:02,655][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:47:03,158][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:47:03,661][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:47:04,164][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:47:04,666][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:47:05,170][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:47:05,673][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:47:06,175][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:47:06,678][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:47:07,180][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:47:07,683][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:47:08,186][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:47:08,689][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:47:09,191][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:47:09,693][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:47:10,194][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:47:10,696][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:47:11,199][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:47:11,703][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:47:12,205][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:47:12,707][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:47:13,210][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:47:13,712][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:47:14,215][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:47:14,717][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:47:15,220][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:47:15,722][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:47:16,225][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:47:16,728][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:47:17,243][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:47:17,745][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:47:18,247][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:47:18,750][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:47:19,253][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:47:19,754][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:47:20,257][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:47:20,759][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:47:21,262][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:47:21,765][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:47:22,268][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:47:22,770][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:47:23,273][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:47:23,775][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:47:24,279][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:47:24,781][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:47:25,286][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21639 tokens. [2026-03-25 17:47:25,922][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-25 17:47:26,668][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:47:26,670][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:47:26,672][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:47:27,368][__main__][INFO] - Iteration 90 took 1m 15s (9.48% Gen, 89.59% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 60h 30m 32s. Estimated total time: 62h 42m 46s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 25s, 500 more iterations: 10h 27m 7s. [2026-03-25 17:47:27,372][__main__][INFO] - Starting iteration 90. [2026-03-25 17:47:27,775][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:47:27,775][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:47:32,983][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:47:34,364][__main__][INFO] - Number of regex retries in iteration 90: 1 [2026-03-25 17:47:34,365][__main__][INFO] - agents played in iteration 90 are Bob, Alice [2026-03-25 17:47:35,336][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:47:36,209][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:47:36,667][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:47:37,176][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:47:37,679][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:47:38,183][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:47:38,685][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:47:39,188][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:47:39,691][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:47:40,194][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:47:40,700][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:47:41,205][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:47:41,711][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:47:42,215][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:47:42,718][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:47:43,222][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:47:43,725][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:47:44,229][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:47:44,732][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:47:45,234][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:47:45,736][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:47:46,238][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:47:46,740][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:47:47,243][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:47:47,746][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:47:48,248][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:47:48,750][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:47:49,251][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:47:49,753][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:47:50,255][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:47:50,757][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:47:51,260][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:47:51,762][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:47:52,264][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:47:52,766][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:47:53,268][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:47:53,770][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:47:54,272][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:47:54,774][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:47:55,277][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:47:55,780][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:47:56,283][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:47:56,786][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:47:57,289][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:47:57,791][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:47:58,295][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:47:58,799][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:47:59,302][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:47:59,806][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:48:00,309][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:48:00,812][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:48:01,315][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:48:01,818][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:48:02,321][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:48:02,824][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:48:03,328][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:48:03,831][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:48:04,335][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:48:04,838][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:48:05,341][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:48:05,844][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:48:06,346][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:48:06,850][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:48:07,352][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:48:07,855][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:48:08,357][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:48:08,862][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:48:09,364][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:48:09,866][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:48:10,368][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:48:10,870][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:48:11,374][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:48:11,877][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:48:12,381][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:48:12,883][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:48:13,387][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:48:13,890][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:48:14,394][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:48:14,899][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:48:15,403][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:48:15,907][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:48:16,410][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:48:16,914][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:48:17,417][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:48:17,920][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:48:18,423][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:48:18,927][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:48:19,430][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:48:19,933][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:48:20,436][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:48:20,938][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:48:21,440][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:48:21,942][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:48:22,444][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:48:22,946][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:48:23,447][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:48:23,949][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:48:24,450][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:48:24,953][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:48:25,455][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:48:25,954][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:48:26,456][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:48:26,959][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:48:27,462][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:48:27,964][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:48:28,467][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:48:28,970][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:48:29,472][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:48:29,975][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:48:30,479][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:48:30,983][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:48:31,486][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:48:31,989][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:48:32,492][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:48:32,994][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:48:33,498][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:48:34,002][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:48:34,505][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:48:35,008][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:48:35,510][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:48:36,012][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:48:36,516][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:48:37,019][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:48:37,522][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:48:38,025][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:48:38,528][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:48:39,030][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:48:39,532][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:48:40,034][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:48:40,536][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21628 tokens. [2026-03-25 17:48:41,176][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-25 17:48:41,910][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:48:41,912][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:48:41,913][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:48:42,611][__main__][INFO] - Iteration 91 took 1m 14s (8.80% Gen, 90.26% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 60h 8m 21s. Estimated total time: 62h 21m 50s. Time estimates for 10 more iterations: 12m 28s, 100 more iterations: 2h 4m 43s, 500 more iterations: 10h 23m 38s. [2026-03-25 17:48:42,613][__main__][INFO] - Starting iteration 91. [2026-03-25 17:48:43,033][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:48:43,034][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:48:47,048][mllm.models.large_language_model_local][WARNING] - Response Given the symmetry and the fact that both you and Alice have similar valuations for the items, it makes sense to propose an equal distribution to ensure we both maximize our points. Here is the proposal: Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:48:49,843][__main__][INFO] - Number of regex retries in iteration 91: 1 [2026-03-25 17:48:49,843][__main__][INFO] - agents played in iteration 91 are Bob, Alice [2026-03-25 17:48:50,830][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:48:51,427][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:48:51,885][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:48:52,391][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:48:52,893][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:48:53,395][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:48:53,898][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:48:54,398][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:48:54,901][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:48:55,403][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:48:55,905][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:48:56,407][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:48:56,908][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:48:57,410][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:48:57,911][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:48:58,412][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:48:58,914][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:48:59,414][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:48:59,918][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:49:00,420][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:49:00,922][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:49:01,424][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:49:01,926][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:49:02,428][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:49:02,930][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:49:03,432][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:49:03,933][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:49:04,436][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:49:04,939][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:49:05,441][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:49:05,945][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:49:06,446][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:49:06,948][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:49:07,449][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:49:07,953][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:49:08,456][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:49:08,958][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:49:09,458][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:49:09,960][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:49:10,461][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:49:10,963][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:49:11,468][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:49:11,969][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:49:12,469][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:49:12,970][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:49:13,471][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:49:13,972][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:49:14,474][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:49:14,974][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:49:15,476][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:49:15,979][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:49:16,482][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:49:16,984][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:49:17,487][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:49:17,989][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:49:18,491][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:49:18,993][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:49:19,495][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:49:19,994][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:49:20,493][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:49:20,992][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:49:21,492][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:49:21,991][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:49:22,490][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:49:22,990][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:49:23,490][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:49:23,992][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:49:24,493][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:49:24,993][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:49:25,494][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:49:25,995][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:49:26,498][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:49:27,000][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:49:27,502][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:49:28,003][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:49:28,505][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:49:29,007][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:49:29,508][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:49:30,009][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:49:30,510][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:49:31,011][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:49:31,511][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:49:32,012][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:49:32,514][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:49:33,016][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:49:33,518][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:49:34,020][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:49:34,522][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:49:35,023][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:49:35,527][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:49:36,029][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:49:36,531][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:49:37,033][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:49:37,534][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:49:38,035][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:49:38,539][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:49:39,041][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:49:39,543][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:49:40,044][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:49:40,545][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:49:41,047][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:49:41,549][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:49:42,051][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:49:42,552][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:49:43,054][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:49:43,555][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:49:44,058][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:49:44,560][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:49:45,061][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:49:45,562][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:49:46,063][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:49:46,563][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:49:47,064][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:49:47,566][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:49:48,067][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:49:48,569][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:49:49,071][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:49:49,572][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:49:50,074][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:49:50,576][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:49:51,079][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:49:51,582][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:49:52,082][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:49:52,583][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:49:53,083][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:49:53,583][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:49:54,083][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:49:54,582][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:49:55,081][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:49:55,582][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 17:49:56,220][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.13%, Current % of VRAM taken: 60.49%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:04 [2026-03-25 17:49:56,956][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:49:56,958][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:49:56,959][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:49:57,837][__main__][INFO] - Iteration 92 took 1m 14s (9.10% Gen, 89.72% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 60h 5m 27s. Estimated total time: 62h 20m 12s. Time estimates for 10 more iterations: 12m 28s, 100 more iterations: 2h 4m 40s, 500 more iterations: 10h 23m 22s. [2026-03-25 17:49:57,839][__main__][INFO] - Starting iteration 92. [2026-03-25 17:49:58,241][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:49:58,242][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:50:04,647][__main__][INFO] - Number of regex retries in iteration 92: 0 [2026-03-25 17:50:04,648][__main__][INFO] - agents played in iteration 92 are Bob, Alice [2026-03-25 17:50:05,622][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:50:06,215][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:50:06,676][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:50:07,185][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:50:07,690][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:50:08,194][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:50:08,700][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:50:09,206][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:50:09,709][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:50:10,212][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:50:10,715][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:50:11,222][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:50:11,727][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:50:12,230][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:50:12,733][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:50:13,235][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:50:13,740][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:50:14,243][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:50:14,744][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:50:15,246][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:50:15,746][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:50:16,247][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:50:16,747][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:50:17,248][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:50:17,749][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:50:18,249][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:50:18,751][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:50:19,251][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:50:19,751][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:50:20,251][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:50:20,751][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:50:21,250][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:50:21,750][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:50:22,252][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:50:22,754][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:50:23,255][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:50:23,755][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:50:24,257][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:50:24,758][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:50:25,259][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:50:25,761][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:50:26,263][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:50:26,766][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:50:27,270][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:50:27,771][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:50:28,273][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:50:28,774][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:50:29,277][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:50:29,779][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:50:30,281][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:50:30,782][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:50:31,284][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:50:31,785][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:50:32,287][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:50:32,788][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:50:33,290][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:50:33,791][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:50:34,292][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:50:34,794][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:50:35,296][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:50:35,799][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:50:36,301][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:50:36,803][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:50:37,308][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:50:37,810][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:50:38,312][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:50:38,816][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:50:39,318][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:50:39,821][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:50:40,325][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:50:40,829][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:50:41,334][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:50:41,838][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:50:42,341][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:50:42,844][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:50:43,347][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:50:43,849][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:50:44,352][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:50:44,855][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:50:45,357][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:50:45,859][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:50:46,362][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:50:46,863][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:50:47,363][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:50:47,863][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:50:48,364][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:50:48,864][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:50:49,364][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:50:49,864][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:50:50,364][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:50:50,864][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:50:51,364][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:50:51,865][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:50:52,366][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:50:52,867][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:50:53,368][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:50:53,869][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:50:54,369][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:50:54,870][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:50:55,370][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:50:55,870][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:50:56,371][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:50:56,871][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:50:57,372][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:50:57,873][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:50:58,374][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:50:58,875][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:50:59,379][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:50:59,882][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:51:00,384][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:51:00,886][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:51:01,388][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:51:01,890][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:51:02,391][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:51:02,893][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:51:03,395][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:51:03,896][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:51:04,398][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:51:04,899][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:51:05,402][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:51:05,901][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:51:06,403][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:51:06,905][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:51:07,408][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:51:07,909][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:51:08,412][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:51:08,914][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:51:09,415][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:51:09,917][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:51:10,418][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21723 tokens. [2026-03-25 17:51:11,049][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:04 [2026-03-25 17:51:11,782][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:51:11,785][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:51:11,786][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:51:13,193][__main__][INFO] - Iteration 93 took 1m 14s (8.55% Gen, 89.57% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 60h 11m 38s. Estimated total time: 62h 27m 38s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 55s, 500 more iterations: 10h 24m 36s. [2026-03-25 17:51:13,195][__main__][INFO] - Starting iteration 93. [2026-03-25 17:51:13,598][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:51:13,599][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:51:20,532][__main__][INFO] - Number of regex retries in iteration 93: 0 [2026-03-25 17:51:20,533][__main__][INFO] - agents played in iteration 93 are Bob, Alice [2026-03-25 17:51:21,500][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:51:22,093][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:51:22,555][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:51:23,061][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:51:23,563][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:51:24,064][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:51:24,565][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:51:25,066][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:51:25,566][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:51:26,067][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:51:26,568][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:51:27,069][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:51:27,569][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:51:28,069][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:51:28,576][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:51:29,080][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:51:29,582][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:51:30,084][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:51:30,586][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:51:31,087][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:51:31,588][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:51:32,090][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:51:32,591][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:51:33,092][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:51:33,592][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:51:34,092][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:51:34,595][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:51:35,098][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:51:35,599][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:51:36,110][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:51:36,612][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:51:37,114][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:51:37,616][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:51:38,118][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:51:38,618][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:51:39,120][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:51:39,621][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:51:40,122][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:51:40,623][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:51:41,125][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:51:41,628][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:51:42,129][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:51:42,629][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:51:43,129][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:51:43,629][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:51:44,131][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:51:44,632][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:51:45,132][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:51:45,632][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:51:46,132][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:51:46,633][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:51:47,135][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:51:47,636][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:51:48,137][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:51:48,638][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:51:49,138][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:51:49,640][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:51:50,141][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:51:50,646][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:51:51,148][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:51:51,649][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:51:52,150][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:51:52,651][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:51:53,152][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:51:53,654][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:51:54,155][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:51:54,656][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:51:55,155][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:51:55,655][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:51:56,156][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:51:56,656][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:51:57,157][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:51:57,657][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:51:58,157][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:51:58,657][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:51:59,159][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:51:59,660][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:52:00,160][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:52:00,660][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:52:01,161][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:52:01,660][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:52:02,161][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:52:02,663][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:52:03,164][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:52:03,664][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:52:04,165][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:52:04,666][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:52:05,165][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:52:05,666][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:52:06,167][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:52:06,668][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:52:07,170][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:52:07,671][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:52:08,172][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:52:08,673][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:52:09,174][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:52:09,675][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:52:10,176][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:52:10,677][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:52:11,178][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:52:11,680][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:52:12,181][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:52:12,681][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:52:13,182][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:52:13,683][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:52:14,184][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:52:14,685][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:52:15,185][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:52:15,686][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:52:16,186][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:52:16,686][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:52:17,187][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:52:17,687][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:52:18,188][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:52:18,689][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:52:19,189][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:52:19,690][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:52:20,191][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:52:20,692][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:52:21,193][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:52:21,695][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:52:22,195][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:52:22,697][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:52:23,198][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:52:23,700][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:52:24,203][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:52:24,704][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:52:25,206][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:52:25,707][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:52:26,208][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21744 tokens. [2026-03-25 17:52:26,838][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 17:52:27,569][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:52:27,571][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:52:27,572][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:52:28,323][__main__][INFO] - Iteration 94 took 1m 14s (9.28% Gen, 89.71% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 59m 1s. Estimated total time: 62h 16m 16s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 32s, 500 more iterations: 10h 22m 42s. [2026-03-25 17:52:28,325][__main__][INFO] - Starting iteration 94. [2026-03-25 17:52:28,728][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:52:28,729][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:52:34,993][__main__][INFO] - Number of regex retries in iteration 94: 0 [2026-03-25 17:52:34,993][__main__][INFO] - agents played in iteration 94 are Bob, Alice [2026-03-25 17:52:35,973][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:52:36,559][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:52:37,017][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:52:37,523][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:52:38,025][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:52:38,526][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:52:39,027][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:52:39,528][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:52:40,029][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:52:40,529][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:52:41,033][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:52:41,537][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:52:42,038][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:52:42,541][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:52:43,043][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:52:43,545][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:52:44,048][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:52:44,550][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:52:45,050][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:52:45,551][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:52:46,051][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:52:46,552][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:52:47,052][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:52:47,553][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:52:48,053][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:52:48,555][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:52:49,056][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:52:49,559][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:52:50,061][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:52:50,562][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:52:51,069][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:52:51,573][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:52:52,078][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:52:52,583][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:52:53,086][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:52:53,589][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:52:54,091][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:52:54,593][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:52:55,095][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:52:55,598][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:52:56,100][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:52:56,603][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:52:57,106][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:52:57,609][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:52:58,111][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:52:58,623][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:52:59,127][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:52:59,630][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:53:00,133][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:53:00,636][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:53:01,141][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:53:01,645][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:53:02,149][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:53:02,652][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:53:03,156][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:53:03,659][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:53:04,163][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:53:04,666][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:53:05,168][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:53:05,671][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:53:06,173][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:53:06,675][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:53:07,177][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:53:07,680][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:53:08,182][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:53:08,685][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:53:09,187][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:53:09,689][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:53:10,191][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:53:10,693][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:53:11,196][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:53:11,700][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:53:12,203][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:53:12,705][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:53:13,208][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:53:13,711][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:53:14,214][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:53:14,717][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:53:15,219][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:53:15,722][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:53:16,225][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:53:16,729][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:53:17,231][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:53:17,733][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:53:18,234][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:53:18,735][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:53:19,238][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:53:19,741][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:53:20,243][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:53:20,745][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:53:21,246][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:53:21,748][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:53:22,251][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:53:22,753][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:53:23,255][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:53:23,757][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:53:24,260][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:53:24,762][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:53:25,264][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:53:25,766][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:53:26,268][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:53:26,770][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:53:27,271][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:53:27,773][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:53:28,275][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:53:28,777][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:53:29,280][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:53:29,783][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:53:30,285][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:53:30,787][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:53:31,290][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:53:31,792][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:53:32,294][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:53:32,795][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:53:33,298][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:53:33,803][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:53:34,306][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:53:34,809][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:53:35,312][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:53:35,814][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:53:36,316][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:53:36,820][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:53:37,324][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:53:37,826][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:53:38,328][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:53:38,830][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:53:39,331][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:53:39,833][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:53:40,334][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:53:40,836][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 17:53:41,468][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:04 [2026-03-25 17:53:42,192][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:53:42,194][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:53:42,196][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:53:42,892][__main__][INFO] - Iteration 95 took 1m 14s (8.45% Gen, 90.61% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 29m 42s. Estimated total time: 61h 48m 12s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 36s, 500 more iterations: 10h 18m 2s. [2026-03-25 17:53:42,894][__main__][INFO] - Starting iteration 95. [2026-03-25 17:53:43,300][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:53:43,300][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:53:49,883][__main__][INFO] - Number of regex retries in iteration 95: 0 [2026-03-25 17:53:49,884][__main__][INFO] - agents played in iteration 95 are Bob, Alice [2026-03-25 17:53:50,845][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:53:51,439][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:53:51,900][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:53:52,408][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:53:52,913][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:53:53,417][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:53:53,922][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:53:54,426][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:53:54,930][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:53:55,435][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:53:55,939][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:53:56,442][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:53:56,945][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:53:57,448][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:53:57,951][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:53:58,454][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:53:58,957][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:53:59,460][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:53:59,962][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:54:00,463][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:54:00,965][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:54:01,468][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:54:01,969][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:54:02,470][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:54:02,971][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:54:03,472][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:54:03,974][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:54:04,478][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:54:04,981][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:54:05,484][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:54:05,987][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:54:06,490][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:54:06,992][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:54:07,495][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:54:07,997][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:54:08,501][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:54:09,003][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:54:09,507][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:54:10,010][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:54:10,512][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:54:11,015][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:54:11,516][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:54:12,022][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:54:12,527][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:54:13,031][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:54:13,534][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:54:14,037][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:54:14,542][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:54:15,046][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:54:15,549][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:54:16,052][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:54:16,553][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:54:17,056][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:54:17,560][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:54:18,062][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:54:18,565][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:54:19,066][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:54:19,567][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:54:20,067][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:54:20,568][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:54:21,068][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:54:21,568][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:54:22,068][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:54:22,568][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:54:23,068][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:54:23,569][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:54:24,072][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:54:24,575][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:54:25,078][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:54:25,582][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:54:26,086][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:54:26,589][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:54:27,092][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:54:27,595][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:54:28,097][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:54:28,601][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:54:29,105][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:54:29,609][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:54:30,111][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:54:30,613][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:54:31,115][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:54:31,618][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:54:32,120][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:54:32,622][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:54:33,124][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:54:33,626][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:54:34,128][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:54:34,630][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:54:35,131][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:54:35,633][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:54:36,136][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:54:36,639][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:54:37,142][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:54:37,646][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:54:38,150][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:54:38,653][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:54:39,155][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:54:39,658][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:54:40,162][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:54:40,663][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:54:41,166][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:54:41,670][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:54:42,172][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:54:42,674][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:54:43,176][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:54:43,678][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:54:44,181][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:54:44,685][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:54:45,187][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:54:45,691][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:54:46,194][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:54:46,697][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:54:47,200][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:54:47,705][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:54:48,207][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:54:48,710][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:54:49,213][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:54:49,716][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:54:50,218][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:54:50,721][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:54:51,223][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:54:51,726][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:54:52,226][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:54:52,727][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:54:53,227][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:54:53,729][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:54:54,229][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:54:54,731][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:54:55,232][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:54:55,732][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-25 17:54:56,377][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 17:54:57,112][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:54:57,115][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:54:57,116][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:54:57,816][__main__][INFO] - Iteration 96 took 1m 14s (8.83% Gen, 90.22% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 46m 15s. Estimated total time: 62h 5m 59s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 11s, 500 more iterations: 10h 20m 59s. [2026-03-25 17:54:57,818][__main__][INFO] - Starting iteration 96. [2026-03-25 17:54:58,218][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:54:58,218][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:54:58,823][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:55:04,940][__main__][INFO] - Number of regex retries in iteration 96: 1 [2026-03-25 17:55:04,941][__main__][INFO] - agents played in iteration 96 are Bob, Alice [2026-03-25 17:55:05,927][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:55:06,524][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:55:06,984][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:55:07,491][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:55:07,993][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:55:08,496][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:55:09,001][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:55:09,504][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:55:10,007][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:55:10,509][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:55:11,013][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:55:11,520][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:55:12,024][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:55:12,528][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:55:13,033][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:55:13,535][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:55:14,040][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:55:14,543][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:55:15,046][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:55:15,548][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:55:16,049][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:55:16,551][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:55:17,053][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:55:17,555][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:55:18,057][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:55:18,558][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:55:19,062][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:55:19,565][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:55:20,068][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:55:20,570][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:55:21,072][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:55:21,574][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:55:22,077][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:55:22,582][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:55:23,083][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:55:23,585][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:55:24,086][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:55:24,587][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:55:25,088][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:55:25,589][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:55:26,089][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:55:26,592][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:55:27,093][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:55:27,595][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:55:28,099][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:55:28,604][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:55:29,107][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:55:29,610][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:55:30,112][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:55:30,614][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:55:31,116][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:55:31,618][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:55:32,120][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:55:32,621][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:55:33,122][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:55:33,623][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:55:34,125][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:55:34,627][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:55:35,130][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:55:35,632][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:55:36,135][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:55:36,637][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:55:37,141][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:55:37,644][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:55:38,146][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:55:38,650][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:55:39,150][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:55:39,650][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:55:40,151][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:55:40,652][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:55:41,154][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:55:41,656][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:55:42,156][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:55:42,656][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:55:43,159][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:55:43,662][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:55:44,164][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:55:44,666][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:55:45,168][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:55:45,669][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:55:46,171][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:55:46,672][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:55:47,174][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:55:47,675][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:55:48,177][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:55:48,680][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:55:49,184][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:55:49,686][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:55:50,188][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:55:50,689][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:55:51,191][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:55:51,692][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:55:52,194][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:55:52,697][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:55:53,199][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:55:53,702][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:55:54,204][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:55:54,707][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:55:55,209][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:55:55,711][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:55:56,212][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:55:56,714][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:55:57,215][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:55:57,717][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:55:58,219][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:55:58,721][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:55:59,224][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:55:59,727][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:56:00,229][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:56:00,731][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:56:01,234][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:56:01,736][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:56:02,238][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:56:02,741][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:56:03,241][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:56:03,742][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:56:04,243][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:56:04,743][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:56:05,245][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:56:05,746][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:56:06,246][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:56:06,748][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:56:07,250][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:56:07,753][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:56:08,255][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:56:08,757][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:56:09,259][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:56:09,763][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:56:10,266][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:56:10,768][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 17:56:11,411][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:04 [2026-03-25 17:56:12,136][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:56:12,138][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:56:12,140][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:56:12,770][__main__][INFO] - Iteration 97 took 1m 14s (9.02% Gen, 90.14% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 46m 39s. Estimated total time: 62h 7m 38s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 15s, 500 more iterations: 10h 21m 16s. [2026-03-25 17:56:12,772][__main__][INFO] - Starting iteration 97. [2026-03-25 17:56:13,175][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:56:13,176][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:56:15,363][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:56:19,771][__main__][INFO] - Number of regex retries in iteration 97: 1 [2026-03-25 17:56:19,772][__main__][INFO] - agents played in iteration 97 are Bob, Alice [2026-03-25 17:56:20,723][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:56:21,325][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:56:21,788][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:56:22,299][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:56:22,805][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:56:23,309][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:56:23,813][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:56:24,317][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:56:24,821][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:56:25,324][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:56:25,829][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:56:26,332][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:56:26,835][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:56:27,339][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:56:27,842][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:56:28,344][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:56:28,847][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:56:29,360][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:56:29,863][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:56:30,365][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:56:30,866][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:56:31,368][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:56:31,869][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:56:32,371][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:56:32,871][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:56:33,372][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:56:33,873][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:56:34,375][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:56:34,875][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:56:35,378][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:56:35,880][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:56:36,382][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:56:36,884][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:56:37,386][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:56:37,888][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:56:38,389][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:56:38,891][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:56:39,393][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:56:39,894][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:56:40,396][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:56:40,897][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:56:41,404][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:56:41,907][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:56:42,409][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:56:42,911][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:56:43,412][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:56:43,916][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:56:44,419][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:56:44,921][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:56:45,423][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:56:45,925][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:56:46,427][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:56:46,928][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:56:47,429][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:56:47,928][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:56:48,429][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:56:48,931][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:56:49,432][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:56:49,935][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:56:50,441][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:56:50,945][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:56:51,450][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:56:51,954][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:56:52,459][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:56:52,962][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:56:53,466][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:56:53,969][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:56:54,470][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:56:54,972][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:56:55,474][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:56:55,977][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:56:56,479][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:56:56,982][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:56:57,484][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:56:57,987][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:56:58,490][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:56:58,994][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:56:59,497][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:57:00,001][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:57:00,505][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:57:01,009][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:57:01,513][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:57:02,014][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:57:02,515][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:57:03,016][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:57:03,518][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:57:04,020][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:57:04,522][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:57:05,024][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:57:05,526][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:57:06,027][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:57:06,529][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:57:07,030][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:57:07,532][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:57:08,035][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:57:08,536][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:57:09,037][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:57:09,541][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:57:10,043][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:57:10,544][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:57:11,046][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:57:11,549][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:57:12,050][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:57:12,552][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:57:13,053][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:57:13,555][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:57:14,055][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:57:14,554][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:57:15,053][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:57:15,554][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:57:16,055][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:57:16,556][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:57:17,055][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:57:17,555][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:57:18,055][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:57:18,556][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:57:19,060][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:57:19,561][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:57:20,063][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:57:20,564][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:57:21,065][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:57:21,566][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:57:22,069][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:57:22,573][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:57:23,077][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:57:23,581][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:57:24,086][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:57:24,590][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:57:25,093][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:57:25,598][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21738 tokens. [2026-03-25 17:57:26,251][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.32%, Current % of VRAM taken: 60.68%, Block Peak % of device VRAM: 62.53%, ΔTime: 00:01:04 [2026-03-25 17:57:27,006][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:57:27,008][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:57:27,009][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:57:27,715][__main__][INFO] - Iteration 98 took 1m 14s (8.85% Gen, 90.20% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 44m 45s. Estimated total time: 62h 7m 0s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 14s, 500 more iterations: 10h 21m 10s. [2026-03-25 17:57:27,717][__main__][INFO] - Starting iteration 98. [2026-03-25 17:57:28,120][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:57:28,121][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:57:33,205][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:57:34,732][__main__][INFO] - Number of regex retries in iteration 98: 1 [2026-03-25 17:57:34,733][__main__][INFO] - agents played in iteration 98 are Bob, Alice [2026-03-25 17:57:35,639][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:57:36,239][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:57:36,700][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:57:37,210][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:57:37,713][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:57:38,216][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:57:38,718][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:57:39,221][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:57:39,724][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:57:40,227][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:57:40,728][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:57:41,230][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:57:41,732][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:57:42,232][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:57:42,734][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:57:43,235][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:57:43,736][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:57:44,236][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:57:44,741][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:57:45,243][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:57:45,746][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:57:46,248][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:57:46,751][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:57:47,252][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:57:47,754][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:57:48,256][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:57:48,758][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:57:49,259][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:57:49,761][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:57:50,262][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:57:50,764][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:57:51,265][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:57:51,768][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:57:52,268][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:57:52,770][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:57:53,272][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:57:53,774][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:57:54,277][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:57:54,780][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:57:55,281][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:57:55,783][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:57:56,285][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:57:56,789][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:57:57,292][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:57:57,796][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:57:58,298][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:57:58,802][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:57:59,306][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:57:59,810][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:58:00,313][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:58:00,815][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:58:01,316][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:58:01,818][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:58:02,321][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:58:02,822][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:58:03,324][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:58:03,826][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:58:04,328][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:58:04,831][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:58:05,332][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:58:05,834][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:58:06,335][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:58:06,837][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:58:07,342][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:58:07,844][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:58:08,347][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:58:08,850][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:58:09,352][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:58:09,856][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:58:10,358][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:58:10,862][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:58:11,366][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:58:11,869][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:58:12,372][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:58:12,871][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:58:13,370][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:58:13,870][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:58:14,370][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:58:14,870][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:58:15,370][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:58:15,871][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:58:16,371][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:58:16,871][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:58:17,373][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:58:17,875][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:58:18,377][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:58:18,878][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:58:19,381][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:58:19,884][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:58:20,386][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:58:20,889][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:58:21,391][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:58:21,892][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:58:22,393][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:58:22,895][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:58:23,397][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:58:23,900][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:58:24,401][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:58:24,903][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:58:25,405][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:58:25,907][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:58:26,409][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:58:26,912][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:58:27,413][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:58:27,915][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:58:28,416][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:58:28,921][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:58:29,424][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:58:29,927][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:58:30,431][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:58:30,933][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:58:31,435][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:58:31,939][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:58:32,442][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:58:32,944][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:58:33,447][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:58:33,949][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:58:34,450][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:58:34,952][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:58:35,455][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:58:35,957][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:58:36,460][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:58:36,962][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:58:37,465][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:58:37,967][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:58:38,470][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:58:38,978][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:58:39,483][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:58:39,987][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:58:40,491][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21738 tokens. [2026-03-25 17:58:41,145][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 17:58:41,870][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:58:41,873][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:58:41,874][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:58:42,707][__main__][INFO] - Iteration 99 took 1m 14s (8.86% Gen, 90.02% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 45m 54s. Estimated total time: 62h 9m 23s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 18s, 500 more iterations: 10h 21m 33s. [2026-03-25 17:58:42,709][__main__][INFO] - Starting iteration 99. [2026-03-25 17:58:43,109][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:58:43,110][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:58:44,231][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:58:44,273][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 17:58:49,740][__main__][INFO] - Number of regex retries in iteration 99: 2 [2026-03-25 17:58:49,741][__main__][INFO] - agents played in iteration 99 are Bob, Alice [2026-03-25 17:58:50,677][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 17:58:51,279][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 17:58:51,737][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 17:58:52,244][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 17:58:52,746][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 17:58:53,248][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 17:58:53,749][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 17:58:54,251][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 17:58:54,753][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 17:58:55,254][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 17:58:55,757][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 17:58:56,259][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 17:58:56,759][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 17:58:57,265][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 17:58:57,766][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 17:58:58,269][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 17:58:58,770][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 17:58:59,273][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 17:58:59,774][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 17:59:00,276][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 17:59:00,778][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 17:59:01,281][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 17:59:01,781][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 17:59:02,283][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 17:59:02,785][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 17:59:03,286][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 17:59:03,788][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 17:59:04,290][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 17:59:04,791][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 17:59:05,293][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 17:59:05,794][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 17:59:06,297][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 17:59:06,799][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 17:59:07,302][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 17:59:07,805][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 17:59:08,307][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 17:59:08,810][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 17:59:09,312][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 17:59:09,814][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 17:59:10,316][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 17:59:10,819][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 17:59:11,322][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 17:59:11,824][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 17:59:12,324][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 17:59:12,825][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 17:59:13,326][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 17:59:13,827][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 17:59:14,328][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 17:59:14,828][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 17:59:15,329][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 17:59:15,831][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 17:59:16,332][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 17:59:16,834][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 17:59:17,336][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 17:59:17,838][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 17:59:18,341][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 17:59:18,845][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 17:59:19,347][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 17:59:19,851][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 17:59:20,353][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 17:59:20,856][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 17:59:21,359][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 17:59:21,862][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 17:59:22,365][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 17:59:22,868][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 17:59:23,370][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 17:59:23,872][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 17:59:24,374][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 17:59:24,875][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 17:59:25,377][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 17:59:25,879][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 17:59:26,380][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 17:59:26,883][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 17:59:27,384][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 17:59:27,886][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 17:59:28,388][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 17:59:28,888][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 17:59:29,390][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 17:59:29,891][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 17:59:30,392][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 17:59:30,895][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 17:59:31,397][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 17:59:31,898][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 17:59:32,399][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 17:59:32,903][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 17:59:33,405][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 17:59:33,906][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 17:59:34,407][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 17:59:34,908][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 17:59:35,409][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 17:59:35,910][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 17:59:36,411][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 17:59:36,913][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 17:59:37,415][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 17:59:37,917][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 17:59:38,418][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 17:59:38,921][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 17:59:39,423][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 17:59:39,925][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 17:59:40,427][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 17:59:40,929][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 17:59:41,433][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 17:59:41,936][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 17:59:42,438][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 17:59:42,941][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 17:59:43,442][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 17:59:43,943][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 17:59:44,444][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 17:59:44,945][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 17:59:45,446][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 17:59:45,947][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 17:59:46,445][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 17:59:46,946][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 17:59:47,446][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 17:59:47,947][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 17:59:48,449][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 17:59:48,951][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 17:59:49,452][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 17:59:49,953][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 17:59:50,454][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 17:59:50,955][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 17:59:51,457][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 17:59:51,960][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 17:59:52,463][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 17:59:52,966][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 17:59:53,469][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 17:59:53,971][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 17:59:54,474][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 17:59:54,976][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 17:59:55,479][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21722 tokens. [2026-03-25 17:59:56,130][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.28%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 17:59:56,864][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 17:59:56,866][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 17:59:56,868][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 17:59:57,510][__main__][INFO] - Iteration 100 took 1m 14s (8.91% Gen, 90.22% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 35m 20s. Estimated total time: 62h 0m 5s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 0s, 500 more iterations: 10h 20m 0s. [2026-03-25 17:59:57,512][__main__][INFO] - Starting iteration 100. [2026-03-25 17:59:57,916][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 1 and human policies 1. [2026-03-25 17:59:57,916][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 17:59:59,066][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:00:04,821][__main__][INFO] - Number of regex retries in iteration 100: 1 [2026-03-25 18:00:04,822][__main__][INFO] - agents played in iteration 100 are Bob, Alice [2026-03-25 18:00:05,804][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:00:06,404][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:00:06,863][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:00:07,369][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:00:07,871][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:00:08,372][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:00:08,873][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:00:09,375][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:00:09,877][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:00:10,379][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:00:10,880][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:00:11,385][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:00:11,887][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:00:12,389][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:00:12,891][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:00:13,394][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:00:13,894][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:00:14,396][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:00:14,902][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:00:15,404][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:00:15,906][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:00:16,408][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:00:16,910][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:00:17,413][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:00:17,917][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:00:18,420][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:00:18,925][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:00:19,429][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:00:19,931][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:00:20,436][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:00:20,939][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:00:21,441][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:00:21,944][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:00:22,446][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:00:22,949][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:00:23,451][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:00:23,953][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:00:24,455][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:00:24,958][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:00:25,461][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:00:25,963][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:00:26,464][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:00:26,966][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:00:27,468][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:00:27,970][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:00:28,471][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:00:28,973][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:00:29,475][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:00:29,976][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:00:30,477][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:00:30,980][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:00:31,481][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:00:31,983][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:00:32,485][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:00:32,987][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:00:33,489][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:00:33,991][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:00:34,492][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:00:34,993][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:00:35,494][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:00:35,995][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:00:36,496][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:00:36,997][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:00:37,500][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:00:38,001][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:00:38,503][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:00:39,004][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:00:39,506][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:00:40,007][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:00:40,508][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:00:41,009][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:00:41,512][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:00:42,013][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:00:42,515][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:00:43,016][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:00:43,517][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:00:44,020][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:00:44,523][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:00:45,025][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:00:45,527][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:00:46,028][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:00:46,529][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:00:47,030][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:00:47,532][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:00:48,035][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:00:48,537][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:00:49,038][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:00:49,540][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:00:50,042][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:00:50,545][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:00:51,046][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:00:51,549][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:00:52,051][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:00:52,553][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:00:53,055][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:00:53,557][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:00:54,058][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:00:54,561][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:00:55,062][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:00:55,564][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:00:56,065][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:00:56,567][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:00:57,068][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:00:57,569][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:00:58,070][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:00:58,572][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:00:59,073][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:00:59,574][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:01:00,076][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:01:00,577][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:01:01,079][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:01:01,581][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:01:02,083][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:01:02,585][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:01:03,087][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:01:03,589][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:01:04,090][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:01:04,594][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:01:05,096][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:01:05,599][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:01:06,100][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:01:06,602][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:01:07,104][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:01:07,606][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:01:08,108][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:01:08,609][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:01:09,110][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:01:09,612][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:01:10,112][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:01:10,612][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21744 tokens. [2026-03-25 18:01:11,283][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 18:01:12,056][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:01:12,058][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:01:12,059][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:01:19,321][__main__][INFO] - Iteration 101 took 1m 21s (8.48% Gen, 82.59% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 65h 24m 11s. Estimated total time: 67h 50m 17s. Time estimates for 10 more iterations: 13m 34s, 100 more iterations: 2h 15m 40s, 500 more iterations: 11h 18m 22s. [2026-03-25 18:01:19,325][__main__][INFO] - Starting iteration 101. [2026-03-25 18:01:19,728][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:01:19,728][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:01:20,342][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:01:26,484][__main__][INFO] - Number of regex retries in iteration 101: 1 [2026-03-25 18:01:26,485][__main__][INFO] - agents played in iteration 101 are Bob, Alice [2026-03-25 18:01:27,442][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:01:28,038][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:01:28,497][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:01:29,006][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:01:29,509][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:01:30,012][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:01:30,515][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:01:31,019][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:01:31,521][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:01:32,024][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:01:32,526][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:01:33,027][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:01:33,530][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:01:34,032][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:01:34,536][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:01:35,037][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:01:35,540][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:01:36,042][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:01:36,544][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:01:37,045][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:01:37,547][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:01:38,048][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:01:38,549][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:01:39,049][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:01:39,551][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:01:40,052][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:01:40,553][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:01:41,053][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:01:41,557][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:01:42,059][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:01:42,561][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:01:43,062][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:01:43,563][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:01:44,065][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:01:44,566][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:01:45,067][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:01:45,569][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:01:46,070][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:01:46,570][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:01:47,070][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:01:47,571][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:01:48,071][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:01:48,573][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:01:49,075][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:01:49,577][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:01:50,079][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:01:50,581][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:01:51,083][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:01:51,585][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:01:52,087][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:01:52,588][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:01:53,088][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:01:53,589][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:01:54,086][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:01:54,587][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:01:55,087][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:01:55,584][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:01:56,087][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:01:56,588][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:01:57,088][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:01:57,588][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:01:58,089][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:01:58,590][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:01:59,091][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:01:59,592][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:02:00,092][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:02:00,593][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:02:01,095][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:02:01,596][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:02:02,098][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:02:02,600][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:02:03,103][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:02:03,606][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:02:04,109][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:02:04,612][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:02:05,113][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:02:05,615][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:02:06,116][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:02:06,620][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:02:07,122][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:02:07,624][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:02:08,126][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:02:08,627][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:02:09,128][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:02:09,629][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:02:10,130][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:02:10,631][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:02:11,133][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:02:11,635][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:02:12,136][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:02:12,636][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:02:13,137][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:02:13,638][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:02:14,140][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:02:14,641][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:02:15,142][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:02:15,644][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:02:16,146][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:02:16,647][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:02:17,149][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:02:17,650][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:02:18,151][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:02:18,651][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:02:19,152][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:02:19,651][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:02:20,152][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:02:20,654][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:02:21,155][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:02:21,657][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:02:22,161][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:02:22,665][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:02:23,168][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:02:23,671][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:02:24,173][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:02:24,672][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:02:25,172][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:02:25,672][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:02:26,172][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:02:26,674][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:02:27,175][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:02:27,675][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:02:28,175][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:02:28,675][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:02:29,176][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:02:29,676][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:02:30,177][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:02:30,678][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:02:31,178][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:02:31,681][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:02:32,182][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21680 tokens. [2026-03-25 18:02:32,840][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-25 18:02:33,575][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:02:33,577][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:02:33,579][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:02:34,424][__main__][INFO] - Iteration 102 took 1m 14s (9.05% Gen, 89.82% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 47m 30s. Estimated total time: 62h 14m 51s. Time estimates for 10 more iterations: 12m 26s, 100 more iterations: 2h 4m 29s, 500 more iterations: 10h 22m 28s. [2026-03-25 18:02:34,426][__main__][INFO] - Starting iteration 102. [2026-03-25 18:02:34,829][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:02:34,829][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:02:39,242][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:02:41,211][__main__][INFO] - Number of regex retries in iteration 102: 1 [2026-03-25 18:02:41,212][__main__][INFO] - agents played in iteration 102 are Bob, Alice [2026-03-25 18:02:42,193][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:02:43,053][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:02:43,512][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:02:44,019][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:02:44,523][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:02:45,026][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:02:45,529][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:02:46,030][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:02:46,532][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:02:47,034][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:02:47,535][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:02:48,037][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:02:48,536][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:02:49,039][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:02:49,540][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:02:50,041][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:02:50,542][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:02:51,042][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:02:51,543][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:02:52,044][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:02:52,545][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:02:53,046][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:02:53,547][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:02:54,048][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:02:54,549][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:02:55,049][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:02:55,549][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:02:56,049][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:02:56,549][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:02:57,046][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:02:57,544][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:02:58,045][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:02:58,545][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:02:59,046][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:02:59,547][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:03:00,049][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:03:00,550][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:03:01,051][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:03:01,551][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:03:02,052][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:03:02,553][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:03:03,054][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:03:03,555][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:03:04,055][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:03:04,557][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:03:05,059][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:03:05,560][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:03:06,061][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:03:06,562][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:03:07,062][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:03:07,563][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:03:08,064][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:03:08,564][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:03:09,065][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:03:09,566][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:03:10,066][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:03:10,567][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:03:11,067][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:03:11,570][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:03:12,072][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:03:12,575][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:03:13,077][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:03:13,578][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:03:14,082][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:03:14,583][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:03:15,086][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:03:15,589][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:03:16,090][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:03:16,592][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:03:17,093][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:03:17,594][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:03:18,097][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:03:18,600][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:03:19,102][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:03:19,603][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:03:20,103][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:03:20,603][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:03:21,103][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:03:21,603][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:03:22,103][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:03:22,603][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:03:23,103][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:03:23,607][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:03:24,109][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:03:24,610][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:03:25,112][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:03:25,613][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:03:26,113][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:03:26,614][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:03:27,115][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:03:27,615][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:03:28,116][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:03:28,617][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:03:29,117][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:03:29,617][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:03:30,116][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:03:30,616][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:03:31,117][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:03:31,618][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:03:32,120][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:03:32,620][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:03:33,121][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:03:33,622][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:03:34,124][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:03:34,625][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:03:35,126][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:03:35,627][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:03:36,128][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:03:36,628][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:03:37,129][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:03:37,629][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:03:38,130][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:03:38,631][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:03:39,132][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:03:39,632][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:03:40,132][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:03:40,632][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:03:41,132][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:03:41,634][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:03:42,135][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:03:42,636][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:03:43,136][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:03:43,639][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:03:44,142][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:03:44,644][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:03:45,146][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:03:45,648][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:03:46,149][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:03:46,651][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:03:47,154][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21697 tokens. [2026-03-25 18:03:47,809][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.32%, Current % of VRAM taken: 60.68%, Block Peak % of device VRAM: 62.50%, ΔTime: 00:01:04 [2026-03-25 18:03:48,534][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:03:48,536][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:03:48,537][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:03:49,232][__main__][INFO] - Iteration 103 took 1m 14s (8.58% Gen, 90.49% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 31m 34s. Estimated total time: 62h 0m 10s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 0s, 500 more iterations: 10h 20m 1s. [2026-03-25 18:03:49,234][__main__][INFO] - Starting iteration 103. [2026-03-25 18:03:49,635][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:03:49,636][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:03:56,230][__main__][INFO] - Number of regex retries in iteration 103: 0 [2026-03-25 18:03:56,231][__main__][INFO] - agents played in iteration 103 are Bob, Alice [2026-03-25 18:03:57,190][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:03:57,782][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:03:58,238][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:03:58,743][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:03:59,244][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:03:59,744][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:04:00,244][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:04:00,744][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:04:01,244][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:04:01,743][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:04:02,243][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:04:02,742][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:04:03,243][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:04:03,743][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:04:04,242][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:04:04,740][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:04:05,239][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:04:05,737][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:04:06,238][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:04:06,740][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:04:07,241][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:04:07,741][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:04:08,242][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:04:08,742][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:04:09,243][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:04:09,744][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:04:10,246][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:04:10,747][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:04:11,250][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:04:11,754][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:04:12,255][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:04:12,756][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:04:13,257][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:04:13,758][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:04:14,258][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:04:14,759][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:04:15,259][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:04:15,759][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:04:16,260][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:04:16,761][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:04:17,261][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:04:17,761][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:04:18,265][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:04:18,767][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:04:19,268][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:04:19,769][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:04:20,270][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:04:20,771][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:04:21,272][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:04:21,772][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:04:22,299][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:04:22,802][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:04:23,306][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:04:23,811][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:04:24,314][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:04:24,817][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:04:25,320][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:04:25,823][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:04:26,324][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:04:26,824][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:04:27,323][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:04:27,823][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:04:28,324][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:04:28,824][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:04:29,325][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:04:29,827][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:04:30,326][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:04:30,826][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:04:31,326][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:04:31,826][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:04:32,326][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:04:32,827][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:04:33,326][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:04:33,826][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:04:34,325][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:04:34,824][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:04:35,323][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:04:35,822][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:04:36,321][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:04:36,821][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:04:37,320][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:04:37,821][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:04:38,321][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:04:38,821][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:04:39,319][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:04:39,820][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:04:40,316][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:04:40,816][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:04:41,319][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:04:41,820][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:04:42,321][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:04:42,822][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:04:43,322][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:04:43,824][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:04:44,324][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:04:44,824][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:04:45,324][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:04:45,826][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:04:46,326][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:04:46,827][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:04:47,327][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:04:47,827][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:04:48,326][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:04:48,827][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:04:49,326][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:04:49,827][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:04:50,328][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:04:50,829][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:04:51,330][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:04:51,831][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:04:52,332][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:04:52,834][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:04:53,336][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:04:53,837][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:04:54,341][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:04:54,843][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:04:55,346][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:04:55,850][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:04:56,352][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:04:56,855][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:04:57,359][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:04:57,862][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:04:58,362][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:04:58,861][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:04:59,361][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:04:59,861][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:05:00,362][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:05:00,862][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:05:01,363][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:05:01,863][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21705 tokens. [2026-03-25 18:05:02,516][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:04 [2026-03-25 18:05:03,246][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:05:03,248][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:05:03,250][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:05:04,107][__main__][INFO] - Iteration 104 took 1m 14s (8.86% Gen, 89.99% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 33m 45s. Estimated total time: 62h 3m 36s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 7s, 500 more iterations: 10h 20m 36s. [2026-03-25 18:05:04,111][__main__][INFO] - Starting iteration 104. [2026-03-25 18:05:04,511][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:05:04,512][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:05:11,004][__main__][INFO] - Number of regex retries in iteration 104: 0 [2026-03-25 18:05:11,005][__main__][INFO] - agents played in iteration 104 are Bob, Alice [2026-03-25 18:05:11,998][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:05:12,585][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:05:13,043][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:05:13,550][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:05:14,053][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:05:14,555][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:05:15,059][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:05:15,561][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:05:16,064][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:05:16,565][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:05:17,066][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:05:17,567][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:05:18,068][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:05:18,569][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:05:19,070][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:05:19,571][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:05:20,072][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:05:20,572][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:05:21,072][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:05:21,571][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:05:22,070][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:05:22,570][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:05:23,070][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:05:23,570][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:05:24,073][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:05:24,574][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:05:25,077][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:05:25,578][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:05:26,080][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:05:26,583][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:05:27,084][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:05:27,585][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:05:28,087][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:05:28,589][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:05:29,088][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:05:29,588][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:05:30,087][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:05:30,586][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:05:31,086][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:05:31,586][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:05:32,085][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:05:32,585][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:05:33,085][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:05:33,585][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:05:34,086][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:05:34,586][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:05:35,087][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:05:35,588][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:05:36,088][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:05:36,588][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:05:37,090][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:05:37,591][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:05:38,092][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:05:38,593][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:05:39,094][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:05:39,595][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:05:40,095][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:05:40,595][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:05:41,096][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:05:41,601][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:05:42,101][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:05:42,603][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:05:43,104][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:05:43,605][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:05:44,106][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:05:44,608][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:05:45,138][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:05:45,648][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:05:46,149][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:05:46,649][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:05:47,152][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:05:47,653][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:05:48,154][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:05:48,656][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:05:49,156][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:05:49,658][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:05:50,159][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:05:50,659][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:05:51,160][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:05:51,664][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:05:52,165][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:05:52,666][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:05:53,167][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:05:53,667][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:05:54,168][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:05:54,667][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:05:55,167][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:05:55,668][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:05:56,168][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:05:56,668][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:05:57,169][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:05:57,668][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:05:58,167][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:05:58,667][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:05:59,168][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:05:59,669][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:06:00,168][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:06:00,668][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:06:01,168][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:06:01,667][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:06:02,166][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:06:02,665][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:06:03,164][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:06:03,663][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:06:04,162][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:06:04,662][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:06:05,163][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:06:05,663][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:06:06,163][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:06:06,663][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:06:07,163][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:06:07,663][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:06:08,164][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:06:08,665][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:06:09,165][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:06:09,665][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:06:10,166][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:06:10,666][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:06:11,167][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:06:11,669][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:06:12,169][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:06:12,669][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:06:13,170][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:06:13,671][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:06:14,171][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:06:14,673][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:06:15,173][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:06:15,672][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:06:16,172][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:06:16,672][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 18:06:17,328][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 18:06:17,957][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:06:17,959][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:06:17,961][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:06:18,714][__main__][INFO] - Iteration 105 took 1m 14s (8.75% Gen, 90.23% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 59h 19m 4s. Estimated total time: 61h 50m 9s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 40s, 500 more iterations: 10h 18m 21s. [2026-03-25 18:06:18,717][__main__][INFO] - Starting iteration 105. [2026-03-25 18:06:19,118][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:06:19,119][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:06:26,042][__main__][INFO] - Number of regex retries in iteration 105: 0 [2026-03-25 18:06:26,043][__main__][INFO] - agents played in iteration 105 are Bob, Alice [2026-03-25 18:06:27,003][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:06:27,589][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:06:28,049][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:06:28,554][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:06:29,054][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:06:29,554][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:06:30,054][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:06:30,554][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:06:31,054][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:06:31,554][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:06:32,056][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:06:32,558][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:06:33,059][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:06:33,561][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:06:34,062][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:06:34,563][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:06:35,063][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:06:35,567][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:06:36,068][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:06:36,568][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:06:37,069][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:06:37,570][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:06:38,070][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:06:38,571][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:06:39,073][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:06:39,574][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:06:40,074][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:06:40,574][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:06:41,074][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:06:41,577][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:06:42,077][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:06:42,578][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:06:43,080][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:06:43,581][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:06:44,083][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:06:44,585][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:06:45,086][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:06:45,588][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:06:46,089][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:06:46,589][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:06:47,089][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:06:47,589][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:06:48,089][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:06:48,588][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:06:49,088][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:06:49,588][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:06:50,087][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:06:50,587][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:06:51,087][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:06:51,586][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:06:52,088][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:06:52,590][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:06:53,093][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:06:53,594][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:06:54,095][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:06:54,596][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:06:55,100][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:06:55,601][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:06:56,101][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:06:56,600][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:06:57,101][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:06:57,601][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:06:58,101][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:06:58,601][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:06:59,101][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:06:59,601][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:07:00,101][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:07:00,603][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:07:01,103][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:07:01,603][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:07:02,103][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:07:02,603][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:07:03,103][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:07:03,604][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:07:04,105][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:07:04,606][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:07:05,108][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:07:05,609][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:07:06,110][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:07:06,611][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:07:07,113][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:07:07,613][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:07:08,114][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:07:08,615][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:07:09,116][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:07:09,618][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:07:10,118][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:07:10,618][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:07:11,121][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:07:11,624][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:07:12,125][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:07:12,627][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:07:13,128][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:07:13,629][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:07:14,129][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:07:14,630][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:07:15,131][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:07:15,633][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:07:16,133][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:07:16,634][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:07:17,135][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:07:17,637][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:07:18,138][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:07:18,639][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:07:19,140][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:07:19,642][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:07:20,141][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:07:20,641][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:07:21,140][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:07:21,640][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:07:22,140][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:07:22,639][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:07:23,139][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:07:23,641][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:07:24,143][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:07:24,645][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:07:25,147][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:07:25,648][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:07:26,149][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:07:26,650][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:07:27,151][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:07:27,652][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:07:28,153][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:07:28,653][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:07:29,153][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:07:29,652][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:07:30,151][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:07:30,649][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:07:31,148][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:07:31,649][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21736 tokens. [2026-03-25 18:07:32,298][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 18:07:33,025][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:07:33,027][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:07:33,029][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:07:33,686][__main__][INFO] - Iteration 106 took 1m 14s (9.28% Gen, 89.83% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 59h 36m 4s. Estimated total time: 62h 8m 24s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 16s, 500 more iterations: 10h 21m 24s. [2026-03-25 18:07:33,688][__main__][INFO] - Starting iteration 106. [2026-03-25 18:07:34,092][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:07:34,093][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:07:35,164][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:07:36,629][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:07:40,486][__main__][INFO] - Number of regex retries in iteration 106: 2 [2026-03-25 18:07:40,487][__main__][INFO] - agents played in iteration 106 are Bob, Alice [2026-03-25 18:07:41,470][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:07:42,055][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:07:42,511][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:07:43,016][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:07:43,515][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:07:44,014][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:07:44,515][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:07:45,014][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:07:45,513][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:07:46,012][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:07:46,514][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:07:47,013][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:07:47,513][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:07:48,012][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:07:48,511][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:07:49,012][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:07:49,512][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:07:50,012][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:07:50,511][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:07:51,011][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:07:51,511][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:07:52,011][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:07:52,511][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:07:53,011][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:07:53,511][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:07:54,011][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:07:54,515][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:07:55,018][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:07:55,520][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:07:56,022][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:07:56,523][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:07:57,025][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:07:57,527][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:07:58,028][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:07:58,530][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:07:59,030][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:07:59,533][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:08:00,035][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:08:00,535][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:08:01,035][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:08:01,536][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:08:02,038][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:08:02,535][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:08:03,032][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:08:03,528][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:08:04,026][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:08:04,523][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:08:05,021][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:08:05,519][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:08:06,016][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:08:06,517][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:08:07,018][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:08:07,519][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:08:08,021][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:08:08,523][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:08:09,025][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:08:09,527][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:08:10,028][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:08:10,528][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:08:11,028][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:08:11,531][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:08:12,032][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:08:12,533][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:08:13,033][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:08:13,533][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:08:14,033][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:08:14,532][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:08:15,032][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:08:15,531][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:08:16,030][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:08:16,529][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:08:17,029][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:08:17,528][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:08:18,028][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:08:18,527][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:08:19,027][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:08:19,526][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:08:20,027][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:08:20,527][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:08:21,027][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:08:21,527][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:08:22,026][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:08:22,526][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:08:23,026][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:08:23,525][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:08:24,025][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:08:24,526][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:08:25,025][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:08:25,526][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:08:26,025][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:08:26,526][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:08:27,027][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:08:27,527][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:08:28,028][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:08:28,528][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:08:29,027][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:08:29,529][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:08:30,030][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:08:30,530][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:08:31,032][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:08:31,531][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:08:32,031][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:08:32,531][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:08:33,030][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:08:33,530][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:08:34,030][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:08:34,527][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:08:35,023][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:08:35,520][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:08:36,016][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:08:36,511][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:08:37,008][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:08:37,506][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:08:38,003][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:08:38,503][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:08:39,003][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:08:39,504][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:08:40,005][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:08:40,506][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:08:41,007][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:08:41,510][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:08:42,011][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:08:42,512][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:08:43,012][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:08:43,512][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:08:44,012][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:08:44,513][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:08:45,013][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:08:45,514][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:08:46,015][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 18:08:46,651][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-25 18:08:47,376][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:08:47,378][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:08:47,380][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:08:48,087][__main__][INFO] - Iteration 107 took 1m 13s (8.64% Gen, 90.40% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 59h 6m 9s. Estimated total time: 61h 39m 44s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 19s, 500 more iterations: 10h 16m 37s. [2026-03-25 18:08:48,089][__main__][INFO] - Starting iteration 107. [2026-03-25 18:08:48,491][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:08:48,492][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:08:55,212][__main__][INFO] - Number of regex retries in iteration 107: 0 [2026-03-25 18:08:55,213][__main__][INFO] - agents played in iteration 107 are Bob, Alice [2026-03-25 18:08:56,172][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:08:56,754][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:08:57,212][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:08:57,718][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:08:58,220][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:08:58,722][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:08:59,225][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:08:59,727][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:09:00,228][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:09:00,730][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:09:01,228][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:09:01,727][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:09:02,226][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:09:02,726][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:09:03,225][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:09:03,724][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:09:04,223][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:09:04,723][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:09:05,224][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:09:05,724][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:09:06,226][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:09:06,727][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:09:07,228][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:09:07,729][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:09:08,229][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:09:08,730][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:09:09,230][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:09:09,730][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:09:10,231][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:09:10,731][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:09:11,233][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:09:11,735][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:09:12,236][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:09:12,736][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:09:13,239][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:09:13,741][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:09:14,243][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:09:14,745][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:09:15,247][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:09:15,749][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:09:16,251][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:09:16,752][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:09:17,252][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:09:17,752][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:09:18,252][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:09:18,753][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:09:19,254][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:09:19,753][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:09:20,253][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:09:20,753][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:09:21,254][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:09:21,755][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:09:22,256][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:09:22,758][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:09:23,259][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:09:23,762][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:09:24,264][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:09:24,765][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:09:25,266][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:09:25,766][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:09:26,267][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:09:26,769][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:09:27,269][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:09:27,770][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:09:28,270][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:09:28,771][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:09:29,273][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:09:29,773][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:09:30,275][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:09:30,778][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:09:31,280][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:09:31,782][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:09:32,286][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:09:32,788][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:09:33,286][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:09:33,785][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:09:34,284][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:09:34,784][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:09:35,283][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:09:35,781][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:09:36,280][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:09:36,778][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:09:37,281][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:09:37,782][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:09:38,283][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:09:38,784][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:09:39,285][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:09:39,785][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:09:40,286][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:09:40,787][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:09:41,289][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:09:41,790][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:09:42,291][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:09:42,791][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:09:43,291][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:09:43,791][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:09:44,292][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:09:44,792][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:09:45,293][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:09:45,795][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:09:46,296][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:09:46,800][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:09:47,302][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:09:47,805][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:09:48,307][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:09:48,810][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:09:49,311][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:09:49,813][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:09:50,315][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:09:50,817][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:09:51,318][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:09:51,820][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:09:52,321][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:09:52,824][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:09:53,326][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:09:53,830][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:09:54,332][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:09:54,835][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:09:55,339][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:09:55,842][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:09:56,345][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:09:56,847][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:09:57,349][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:09:57,851][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:09:58,353][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:09:58,854][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:09:59,356][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:09:59,857][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:10:00,359][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:10:00,860][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21726 tokens. [2026-03-25 18:10:01,490][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-25 18:10:02,219][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:10:02,221][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:10:02,224][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:10:03,027][__main__][INFO] - Iteration 108 took 1m 14s (9.02% Gen, 89.90% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 31m 59s. Estimated total time: 62h 6m 49s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 13s, 500 more iterations: 10h 21m 8s. [2026-03-25 18:10:03,029][__main__][INFO] - Starting iteration 108. [2026-03-25 18:10:03,429][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:10:03,430][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:10:05,697][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:10:09,696][__main__][INFO] - Number of regex retries in iteration 108: 1 [2026-03-25 18:10:09,697][__main__][INFO] - agents played in iteration 108 are Bob, Alice [2026-03-25 18:10:10,609][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:10:11,197][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:10:11,656][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:10:12,164][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:10:12,666][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:10:13,169][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:10:13,672][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:10:14,177][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:10:14,680][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:10:15,184][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:10:15,687][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:10:16,189][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:10:16,692][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:10:17,195][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:10:17,697][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:10:18,199][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:10:18,703][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:10:19,204][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:10:19,704][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:10:20,205][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:10:20,706][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:10:21,207][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:10:21,707][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:10:22,208][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:10:22,708][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:10:23,208][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:10:23,711][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:10:24,211][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:10:24,712][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:10:25,212][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:10:25,712][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:10:26,212][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:10:26,712][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:10:27,213][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:10:27,712][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:10:28,212][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:10:28,711][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:10:29,210][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:10:29,709][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:10:30,208][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:10:30,709][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:10:31,208][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:10:31,709][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:10:32,210][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:10:32,711][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:10:33,214][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:10:33,715][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:10:34,215][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:10:34,715][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:10:35,216][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:10:35,715][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:10:36,215][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:10:36,715][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:10:37,214][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:10:37,715][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:10:38,215][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:10:38,715][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:10:39,214][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:10:39,713][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:10:40,212][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:10:40,711][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:10:41,211][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:10:41,712][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:10:42,212][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:10:42,711][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:10:43,210][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:10:43,710][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:10:44,211][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:10:44,713][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:10:45,214][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:10:45,715][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:10:46,216][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:10:46,718][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:10:47,220][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:10:47,721][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:10:48,221][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:10:48,721][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:10:49,221][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:10:49,721][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:10:50,223][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:10:50,723][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:10:51,223][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:10:51,723][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:10:52,223][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:10:52,721][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:10:53,220][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:10:53,721][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:10:54,221][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:10:54,721][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:10:55,221][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:10:55,719][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:10:56,218][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:10:56,716][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:10:57,215][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:10:57,714][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:10:58,213][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:10:58,713][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:10:59,212][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:10:59,712][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:11:00,210][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:11:00,709][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:11:01,209][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:11:01,708][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:11:02,208][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:11:02,707][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:11:03,207][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:11:03,707][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:11:04,208][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:11:04,709][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:11:05,210][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:11:05,711][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:11:06,211][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:11:06,711][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:11:07,212][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:11:07,711][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:11:08,210][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:11:08,709][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:11:09,210][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:11:09,709][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:11:10,209][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:11:10,709][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:11:11,210][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:11:11,710][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:11:12,209][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:11:12,709][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:11:13,208][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:11:13,707][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:11:14,207][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:11:14,707][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:11:15,206][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 18:11:15,829][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 18:11:16,559][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:11:16,561][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:11:16,563][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:11:17,194][__main__][INFO] - Iteration 109 took 1m 13s (8.50% Gen, 90.65% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 52m 11s. Estimated total time: 61h 28m 15s. Time estimates for 10 more iterations: 12m 17s, 100 more iterations: 2h 2m 56s, 500 more iterations: 10h 14m 42s. [2026-03-25 18:11:17,196][__main__][INFO] - Starting iteration 109. [2026-03-25 18:11:17,594][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:11:17,595][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:11:23,884][__main__][INFO] - Number of regex retries in iteration 109: 0 [2026-03-25 18:11:23,885][__main__][INFO] - agents played in iteration 109 are Bob, Alice [2026-03-25 18:11:24,826][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:11:25,406][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:11:25,863][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:11:26,369][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:11:26,870][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:11:27,371][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:11:27,870][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:11:28,371][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:11:28,872][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:11:29,373][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:11:29,875][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:11:30,375][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:11:30,875][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:11:31,376][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:11:31,877][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:11:32,378][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:11:32,879][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:11:33,380][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:11:33,881][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:11:34,382][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:11:34,883][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:11:35,383][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:11:35,884][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:11:36,383][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:11:36,883][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:11:37,385][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:11:37,886][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:11:38,388][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:11:38,890][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:11:39,390][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:11:39,891][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:11:40,392][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:11:40,893][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:11:41,397][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:11:41,898][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:11:42,398][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:11:42,897][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:11:43,397][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:11:43,895][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:11:44,395][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:11:44,893][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:11:45,391][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:11:45,891][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:11:46,391][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:11:46,890][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:11:47,389][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:11:47,889][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:11:48,388][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:11:48,888][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:11:49,388][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:11:49,889][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:11:50,388][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:11:50,887][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:11:51,386][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:11:51,886][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:11:52,385][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:11:52,884][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:11:53,384][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:11:53,883][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:11:54,383][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:11:54,883][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:11:55,383][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:11:55,882][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:11:56,382][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:11:56,881][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:11:57,381][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:11:57,879][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:11:58,379][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:11:58,881][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:11:59,382][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:11:59,882][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:12:00,383][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:12:00,883][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:12:01,383][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:12:01,884][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:12:02,384][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:12:02,884][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:12:03,384][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:12:03,885][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:12:04,386][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:12:04,887][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:12:05,387][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:12:05,887][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:12:06,386][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:12:06,886][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:12:07,385][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:12:07,884][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:12:08,384][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:12:08,884][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:12:09,383][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:12:09,884][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:12:10,385][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:12:10,886][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:12:11,389][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:12:11,889][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:12:12,389][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:12:12,890][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:12:13,390][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:12:13,890][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:12:14,389][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:12:14,887][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:12:15,387][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:12:15,886][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:12:16,385][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:12:16,884][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:12:17,383][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:12:17,883][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:12:18,383][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:12:18,883][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:12:19,384][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:12:19,883][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:12:20,383][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:12:20,884][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:12:21,383][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:12:21,883][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:12:22,382][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:12:22,883][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:12:23,384][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:12:23,885][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:12:24,385][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:12:24,886][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:12:25,387][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:12:25,886][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:12:26,385][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:12:26,884][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:12:27,383][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:12:27,882][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:12:28,382][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:12:28,881][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:12:29,380][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21708 tokens. [2026-03-25 18:12:30,006][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-25 18:12:30,733][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:12:30,735][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:12:30,737][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:12:31,420][__main__][INFO] - Iteration 110 took 1m 13s (8.52% Gen, 90.55% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 54m 0s. Estimated total time: 61h 31m 18s. Time estimates for 10 more iterations: 12m 18s, 100 more iterations: 2h 3m 2s, 500 more iterations: 10h 15m 13s. [2026-03-25 18:12:31,422][__main__][INFO] - Starting iteration 110. [2026-03-25 18:12:31,823][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:12:31,824][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:12:32,417][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:12:34,499][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:12:38,396][__main__][INFO] - Number of regex retries in iteration 110: 2 [2026-03-25 18:12:38,396][__main__][INFO] - agents played in iteration 110 are Bob, Alice [2026-03-25 18:12:39,350][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:12:39,928][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:12:40,385][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:12:40,890][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:12:41,392][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:12:41,892][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:12:42,392][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:12:42,892][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:12:43,391][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:12:43,891][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:12:44,391][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:12:44,891][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:12:45,391][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:12:45,891][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:12:46,390][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:12:46,888][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:12:47,388][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:12:47,888][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:12:48,387][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:12:48,886][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:12:49,386][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:12:49,884][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:12:50,384][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:12:50,883][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:12:51,383][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:12:51,882][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:12:52,383][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:12:52,883][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:12:53,383][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:12:53,883][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:12:54,383][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:12:54,883][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:12:55,384][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:12:55,884][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:12:56,380][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:12:56,877][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:12:57,372][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:12:57,868][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:12:58,364][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:12:58,860][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:12:59,355][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:12:59,851][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:13:00,350][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:13:00,849][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:13:01,347][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:13:01,847][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:13:02,345][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:13:02,845][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:13:03,344][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:13:03,844][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:13:04,345][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:13:04,846][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:13:05,346][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:13:05,847][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:13:06,347][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:13:06,848][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:13:07,350][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:13:07,850][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:13:08,349][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:13:08,849][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:13:09,347][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:13:09,847][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:13:10,347][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:13:10,846][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:13:11,347][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:13:11,848][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:13:12,348][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:13:12,848][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:13:13,347][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:13:13,846][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:13:14,347][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:13:14,846][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:13:15,346][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:13:15,846][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:13:16,346][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:13:16,846][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:13:17,346][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:13:17,846][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:13:18,346][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:13:18,847][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:13:19,347][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:13:19,847][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:13:20,346][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:13:20,845][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:13:21,344][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:13:21,843][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:13:22,342][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:13:22,841][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:13:23,340][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:13:23,839][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:13:24,338][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:13:24,837][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:13:25,336][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:13:25,836][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:13:26,336][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:13:26,836][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:13:27,335][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:13:27,835][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:13:28,330][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:13:28,827][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:13:29,324][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:13:29,820][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:13:30,317][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:13:30,813][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:13:31,310][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:13:31,807][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:13:32,306][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:13:32,806][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:13:33,307][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:13:33,807][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:13:34,307][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:13:34,806][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:13:35,307][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:13:35,808][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:13:36,310][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:13:36,810][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:13:37,311][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:13:37,811][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:13:38,313][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:13:38,814][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:13:39,314][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:13:39,814][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:13:40,314][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:13:40,813][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:13:41,314][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:13:41,814][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:13:42,314][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:13:42,814][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:13:43,314][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:13:43,813][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21716 tokens. [2026-03-25 18:13:44,424][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 18:13:45,149][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:13:45,151][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:13:45,152][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:13:45,942][__main__][INFO] - Iteration 111 took 1m 14s (8.87% Gen, 90.06% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 59h 7m 26s. Estimated total time: 61h 45m 59s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 31s, 500 more iterations: 10h 17m 39s. [2026-03-25 18:13:45,944][__main__][INFO] - Starting iteration 111. [2026-03-25 18:13:46,345][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:13:46,346][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:13:52,939][__main__][INFO] - Number of regex retries in iteration 111: 0 [2026-03-25 18:13:52,940][__main__][INFO] - agents played in iteration 111 are Bob, Alice [2026-03-25 18:13:53,889][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:13:54,472][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:13:54,928][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:13:55,431][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:13:55,929][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:13:56,427][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:13:56,926][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:13:57,425][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:13:57,924][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:13:58,422][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:13:58,923][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:13:59,424][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:13:59,924][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:14:00,424][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:14:00,924][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:14:01,424][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:14:01,924][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:14:02,424][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:14:02,926][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:14:03,428][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:14:03,928][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:14:04,429][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:14:04,929][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:14:05,428][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:14:05,928][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:14:06,425][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:14:06,922][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:14:07,420][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:14:07,920][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:14:08,418][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:14:08,916][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:14:09,414][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:14:09,911][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:14:10,409][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:14:10,907][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:14:11,408][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:14:11,908][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:14:12,407][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:14:12,906][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:14:13,406][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:14:13,905][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:14:14,404][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:14:14,904][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:14:15,404][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:14:15,904][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:14:16,404][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:14:16,904][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:14:17,404][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:14:17,904][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:14:18,404][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:14:18,904][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:14:19,403][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:14:19,903][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:14:20,403][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:14:20,904][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:14:21,404][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:14:21,903][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:14:22,403][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:14:22,903][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:14:23,404][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:14:23,905][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:14:24,405][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:14:24,907][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:14:25,407][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:14:25,908][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:14:26,410][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:14:26,910][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:14:27,410][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:14:27,910][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:14:28,411][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:14:28,912][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:14:29,413][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:14:29,913][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:14:30,413][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:14:30,912][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:14:31,412][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:14:31,912][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:14:32,412][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:14:32,912][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:14:33,412][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:14:33,912][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:14:34,412][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:14:34,912][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:14:35,412][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:14:35,913][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:14:36,416][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:14:36,918][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:14:37,420][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:14:37,921][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:14:38,422][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:14:38,922][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:14:39,421][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:14:39,921][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:14:40,419][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:14:40,918][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:14:41,418][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:14:41,919][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:14:42,419][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:14:42,918][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:14:43,417][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:14:43,916][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:14:44,416][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:14:44,914][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:14:45,412][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:14:45,911][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:14:46,410][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:14:46,909][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:14:47,409][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:14:47,908][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:14:48,408][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:14:48,908][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:14:49,408][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:14:49,907][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:14:50,407][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:14:50,907][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:14:51,406][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:14:51,906][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:14:52,405][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:14:52,905][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:14:53,404][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:14:53,903][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:14:54,403][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:14:54,903][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:14:55,404][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:14:55,904][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:14:56,405][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:14:56,905][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:14:57,406][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:14:57,906][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:14:58,407][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21728 tokens. [2026-03-25 18:14:59,025][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.28%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 18:14:59,750][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:14:59,752][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:14:59,753][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:15:00,404][__main__][INFO] - Iteration 112 took 1m 14s (8.90% Gen, 90.21% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 59h 3m 12s. Estimated total time: 61h 42m 59s. Time estimates for 10 more iterations: 12m 20s, 100 more iterations: 2h 3m 25s, 500 more iterations: 10h 17m 9s. [2026-03-25 18:15:00,406][__main__][INFO] - Starting iteration 112. [2026-03-25 18:15:00,811][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:15:00,811][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:15:07,056][__main__][INFO] - Number of regex retries in iteration 112: 0 [2026-03-25 18:15:07,057][__main__][INFO] - agents played in iteration 112 are Bob, Alice [2026-03-25 18:15:08,030][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:15:08,609][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:15:09,066][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:15:09,571][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:15:10,072][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:15:10,572][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:15:11,073][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:15:11,575][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:15:12,076][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:15:12,577][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:15:13,076][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:15:13,576][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:15:14,076][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:15:14,576][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:15:15,076][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:15:15,575][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:15:16,075][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:15:16,576][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:15:17,074][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:15:17,573][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:15:18,072][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:15:18,570][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:15:19,069][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:15:19,567][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:15:20,066][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:15:20,564][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:15:21,064][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:15:21,563][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:15:22,063][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:15:22,562][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:15:23,062][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:15:23,562][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:15:24,061][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:15:24,561][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:15:25,061][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:15:25,560][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:15:26,059][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:15:26,558][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:15:27,056][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:15:27,555][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:15:28,055][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:15:28,553][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:15:29,052][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:15:29,551][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:15:30,049][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:15:30,548][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:15:31,047][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:15:31,546][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:15:32,044][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:15:32,543][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:15:33,043][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:15:33,542][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:15:34,041][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:15:34,540][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:15:35,038][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:15:35,538][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:15:36,039][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:15:36,538][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:15:37,039][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:15:37,538][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:15:38,037][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:15:38,538][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:15:39,039][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:15:39,539][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:15:40,038][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:15:40,538][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:15:41,038][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:15:41,541][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:15:42,042][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:15:42,543][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:15:43,044][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:15:43,544][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:15:44,045][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:15:44,545][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:15:45,044][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:15:45,545][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:15:46,044][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:15:46,544][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:15:47,044][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:15:47,543][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:15:48,043][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:15:48,544][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:15:49,042][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:15:49,541][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:15:50,040][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:15:50,539][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:15:51,038][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:15:51,536][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:15:52,034][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:15:52,532][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:15:53,031][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:15:53,530][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:15:54,029][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:15:54,529][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:15:55,029][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:15:55,528][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:15:56,028][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:15:56,528][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:15:57,027][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:15:57,526][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:15:58,025][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:15:58,525][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:15:59,024][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:15:59,523][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:16:00,022][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:16:00,520][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:16:01,021][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:16:01,520][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:16:02,019][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:16:02,518][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:16:03,019][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:16:03,518][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:16:04,016][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:16:04,515][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:16:05,014][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:16:05,513][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:16:06,012][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:16:06,511][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:16:07,011][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:16:07,511][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:16:08,010][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:16:08,510][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:16:09,010][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:16:09,510][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:16:10,010][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:16:10,509][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:16:11,008][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:16:11,510][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:16:12,009][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:16:12,510][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 18:16:13,119][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-25 18:16:13,848][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:16:13,851][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:16:13,852][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:16:14,587][__main__][INFO] - Iteration 113 took 1m 13s (8.47% Gen, 90.54% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 47m 48s. Estimated total time: 61h 28m 49s. Time estimates for 10 more iterations: 12m 17s, 100 more iterations: 2h 2m 57s, 500 more iterations: 10h 14m 48s. [2026-03-25 18:16:14,589][__main__][INFO] - Starting iteration 113. [2026-03-25 18:16:14,989][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:16:14,990][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:16:21,931][__main__][INFO] - Number of regex retries in iteration 113: 0 [2026-03-25 18:16:21,932][__main__][INFO] - agents played in iteration 113 are Bob, Alice [2026-03-25 18:16:22,881][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:16:23,455][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:16:23,911][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:16:24,416][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:16:24,915][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:16:25,414][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:16:25,913][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:16:26,411][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:16:26,910][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:16:27,409][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:16:27,911][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:16:28,411][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:16:28,911][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:16:29,412][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:16:29,912][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:16:30,412][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:16:30,912][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:16:31,412][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:16:31,914][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:16:32,415][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:16:32,915][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:16:33,415][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:16:33,915][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:16:34,416][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:16:34,916][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:16:35,417][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:16:35,917][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:16:36,415][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:16:36,914][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:16:37,414][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:16:37,912][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:16:38,413][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:16:38,913][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:16:39,413][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:16:39,931][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:16:40,436][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:16:40,936][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:16:41,440][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:16:41,941][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:16:42,443][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:16:42,944][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:16:43,444][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:16:43,945][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:16:44,445][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:16:44,946][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:16:45,446][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:16:45,947][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:16:46,447][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:16:46,948][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:16:47,449][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:16:47,948][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:16:48,447][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:16:48,946][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:16:49,445][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:16:49,943][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:16:50,442][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:16:50,941][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:16:51,439][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:16:51,940][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:16:52,439][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:16:52,938][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:16:53,436][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:16:53,935][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:16:54,434][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:16:54,934][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:16:55,433][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:16:55,931][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:16:56,430][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:16:56,928][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:16:57,428][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:16:57,927][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:16:58,426][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:16:58,925][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:16:59,424][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:16:59,924][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:17:00,425][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:17:00,925][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:17:01,425][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:17:01,925][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:17:02,425][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:17:02,926][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:17:03,426][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:17:03,926][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:17:04,427][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:17:04,928][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:17:05,428][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:17:05,929][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:17:06,429][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:17:06,930][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:17:07,429][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:17:07,928][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:17:08,427][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:17:08,926][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:17:09,424][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:17:09,923][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:17:10,422][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:17:10,919][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:17:11,419][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:17:11,920][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:17:12,422][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:17:12,923][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:17:13,423][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:17:13,924][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:17:14,424][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:17:14,924][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:17:15,425][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:17:15,925][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:17:16,426][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:17:16,927][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:17:17,428][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:17:17,929][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:17:18,429][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:17:18,930][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:17:19,430][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:17:19,929][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:17:20,427][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:17:20,925][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:17:21,423][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:17:21,921][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:17:22,419][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:17:22,919][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:17:23,418][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:17:23,918][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:17:24,418][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:17:24,918][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:17:25,417][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:17:25,917][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:17:26,416][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:17:26,915][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:17:27,414][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21722 tokens. [2026-03-25 18:17:28,019][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:04 [2026-03-25 18:17:28,750][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:17:28,752][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:17:28,753][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:17:29,548][__main__][INFO] - Iteration 114 took 1m 14s (9.31% Gen, 89.62% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 59h 25m 43s. Estimated total time: 62h 7m 59s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 15s, 500 more iterations: 10h 21m 19s. [2026-03-25 18:17:29,550][__main__][INFO] - Starting iteration 114. [2026-03-25 18:17:29,953][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:17:29,954][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:17:33,198][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 1, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:17:36,568][__main__][INFO] - Number of regex retries in iteration 114: 1 [2026-03-25 18:17:36,569][__main__][INFO] - agents played in iteration 114 are Bob, Alice [2026-03-25 18:17:37,549][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:17:38,127][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:17:38,583][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:17:39,088][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:17:39,589][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:17:40,090][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:17:40,592][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:17:41,093][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:17:41,595][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:17:42,096][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:17:42,597][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:17:43,098][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:17:43,599][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:17:44,100][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:17:44,603][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:17:45,104][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:17:45,605][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:17:46,106][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:17:46,607][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:17:47,107][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:17:47,607][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:17:48,108][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:17:48,609][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:17:49,109][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:17:49,610][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:17:50,111][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:17:50,611][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:17:51,111][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:17:51,611][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:17:52,112][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:17:52,612][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:17:53,113][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:17:53,614][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:17:54,115][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:17:54,617][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:17:55,120][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:17:55,623][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:17:56,125][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:17:56,628][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:17:57,130][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:17:57,632][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:17:58,133][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:17:58,632][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:17:59,131][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:17:59,630][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:18:00,129][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:18:00,627][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:18:01,126][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:18:01,625][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:18:02,124][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:18:02,625][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:18:03,127][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:18:03,629][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:18:04,130][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:18:04,631][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:18:05,133][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:18:05,634][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:18:06,135][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:18:06,640][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:18:07,144][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:18:07,646][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:18:08,149][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:18:08,653][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:18:09,156][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:18:09,659][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:18:10,163][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:18:10,664][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:18:11,165][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:18:11,667][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:18:12,168][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:18:12,668][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:18:13,168][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:18:13,669][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:18:14,170][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:18:14,670][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:18:15,170][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:18:15,671][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:18:16,171][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:18:16,670][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:18:17,170][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:18:17,670][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:18:18,171][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:18:18,671][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:18:19,172][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:18:19,672][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:18:20,171][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:18:20,671][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:18:21,170][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:18:21,671][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:18:22,170][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:18:22,670][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:18:23,169][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:18:23,668][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:18:24,168][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:18:24,667][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:18:25,166][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:18:25,666][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:18:26,166][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:18:26,667][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:18:27,168][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:18:27,670][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:18:28,171][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:18:28,673][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:18:29,174][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:18:29,676][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:18:30,177][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:18:30,677][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:18:31,177][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:18:31,677][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:18:32,176][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:18:32,675][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:18:33,174][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:18:33,673][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:18:34,171][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:18:34,671][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:18:35,172][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:18:35,674][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:18:36,174][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:18:36,675][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:18:37,177][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:18:37,679][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:18:38,183][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:18:38,685][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:18:39,187][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:18:39,691][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:18:40,193][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:18:40,695][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:18:41,198][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:18:41,702][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:18:42,207][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21738 tokens. [2026-03-25 18:18:42,821][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.32%, Current % of VRAM taken: 60.68%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:04 [2026-03-25 18:18:43,548][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:18:43,550][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:18:43,552][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:18:44,181][__main__][INFO] - Iteration 115 took 1m 14s (8.91% Gen, 90.24% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 59h 7m 54s. Estimated total time: 61h 51m 25s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 42s, 500 more iterations: 10h 18m 34s. [2026-03-25 18:18:44,183][__main__][INFO] - Starting iteration 115. [2026-03-25 18:18:44,587][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:18:44,588][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:18:46,312][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:18:49,496][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:18:50,857][__main__][INFO] - Number of regex retries in iteration 115: 2 [2026-03-25 18:18:50,858][__main__][INFO] - agents played in iteration 115 are Bob, Alice [2026-03-25 18:18:52,085][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:18:52,667][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:18:53,123][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:18:53,628][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:18:54,128][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:18:54,628][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:18:55,128][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:18:55,630][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:18:56,130][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:18:56,631][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:18:57,133][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:18:57,634][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:18:58,135][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:18:58,636][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:18:59,137][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:18:59,639][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:19:00,140][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:19:00,643][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:19:01,143][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:19:01,644][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:19:02,144][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:19:02,644][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:19:03,145][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:19:03,645][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:19:04,146][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:19:04,647][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:19:05,147][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:19:05,647][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:19:06,147][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:19:06,647][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:19:07,150][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:19:07,650][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:19:08,151][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:19:08,652][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:19:09,152][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:19:09,651][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:19:10,151][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:19:10,652][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:19:11,153][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:19:11,655][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:19:12,155][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:19:12,655][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:19:13,154][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:19:13,654][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:19:14,153][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:19:14,653][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:19:15,153][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:19:15,652][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:19:16,151][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:19:16,651][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:19:17,153][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:19:17,655][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:19:18,156][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:19:18,658][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:19:19,159][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:19:19,660][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:19:20,162][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:19:20,664][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:19:21,164][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:19:21,664][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:19:22,164][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:19:22,664][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:19:23,164][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:19:23,664][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:19:24,164][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:19:24,664][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:19:25,165][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:19:25,665][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:19:26,165][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:19:26,665][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:19:27,165][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:19:27,664][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:19:28,164][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:19:28,663][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:19:29,164][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:19:29,665][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:19:30,165][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:19:30,665][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:19:31,165][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:19:31,666][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:19:32,166][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:19:32,666][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:19:33,165][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:19:33,664][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:19:34,163][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:19:34,662][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:19:35,161][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:19:35,662][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:19:36,161][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:19:36,660][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:19:37,159][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:19:37,657][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:19:38,157][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:19:38,656][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:19:39,155][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:19:39,655][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:19:40,154][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:19:40,653][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:19:41,153][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:19:41,653][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:19:42,155][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:19:42,656][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:19:43,157][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:19:43,657][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:19:44,156][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:19:44,655][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:19:45,153][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:19:45,651][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:19:46,151][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:19:46,650][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:19:47,149][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:19:47,648][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:19:48,147][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:19:48,647][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:19:49,148][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:19:49,648][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:19:50,149][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:19:50,651][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:19:51,152][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:19:51,652][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:19:52,152][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:19:52,655][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:19:53,154][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:19:53,654][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:19:54,152][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:19:54,652][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:19:55,152][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:19:55,652][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:19:56,152][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:19:56,651][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21736 tokens. [2026-03-25 18:19:57,270][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-25 18:19:57,996][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:19:57,998][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:19:58,000][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:19:58,730][__main__][INFO] - Iteration 116 took 1m 14s (8.46% Gen, 90.56% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 2m 24s. Estimated total time: 61h 47m 10s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 34s, 500 more iterations: 10h 17m 51s. [2026-03-25 18:19:58,732][__main__][INFO] - Starting iteration 116. [2026-03-25 18:19:59,135][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:19:59,136][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:19:59,732][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:20:05,617][__main__][INFO] - Number of regex retries in iteration 116: 1 [2026-03-25 18:20:05,618][__main__][INFO] - agents played in iteration 116 are Bob, Alice [2026-03-25 18:20:06,593][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:20:07,173][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:20:07,629][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:20:08,133][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:20:08,634][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:20:09,134][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:20:09,634][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:20:10,134][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:20:10,633][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:20:11,133][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:20:11,634][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:20:12,133][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:20:12,633][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:20:13,132][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:20:13,631][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:20:14,131][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:20:14,630][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:20:15,129][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:20:15,632][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:20:16,133][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:20:16,633][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:20:17,133][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:20:17,633][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:20:18,133][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:20:18,634][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:20:19,135][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:20:19,634][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:20:20,134][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:20:20,633][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:20:21,132][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:20:21,631][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:20:22,130][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:20:22,630][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:20:23,129][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:20:23,628][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:20:24,128][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:20:24,627][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:20:25,127][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:20:25,626][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:20:26,125][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:20:26,625][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:20:27,125][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:20:27,625][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:20:28,125][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:20:28,627][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:20:29,129][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:20:29,631][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:20:30,132][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:20:30,633][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:20:31,133][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:20:31,631][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:20:32,130][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:20:32,630][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:20:33,130][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:20:33,629][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:20:34,129][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:20:34,628][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:20:35,127][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:20:35,624][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:20:36,121][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:20:36,619][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:20:37,119][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:20:37,617][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:20:38,114][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:20:38,612][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:20:39,109][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:20:39,609][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:20:40,108][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:20:40,608][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:20:41,108][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:20:41,610][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:20:42,109][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:20:42,609][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:20:43,110][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:20:43,611][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:20:44,111][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:20:44,612][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:20:45,111][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:20:45,611][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:20:46,110][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:20:46,610][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:20:47,111][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:20:47,611][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:20:48,111][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:20:48,612][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:20:49,113][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:20:49,613][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:20:50,113][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:20:50,613][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:20:51,114][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:20:51,614][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:20:52,114][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:20:52,613][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:20:53,112][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:20:53,611][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:20:54,111][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:20:54,610][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:20:55,110][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:20:55,609][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:20:56,108][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:20:56,607][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:20:57,106][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:20:57,605][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:20:58,105][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:20:58,604][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:20:59,104][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:20:59,603][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:21:00,103][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:21:00,603][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:21:01,103][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:21:01,603][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:21:02,104][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:21:02,604][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:21:03,103][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:21:03,602][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:21:04,103][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:21:04,603][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:21:05,104][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:21:05,604][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:21:06,104][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:21:06,603][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:21:07,103][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:21:07,600][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:21:08,097][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:21:08,593][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:21:09,090][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:21:09,588][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:21:10,085][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:21:10,582][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:21:11,080][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21585 tokens. [2026-03-25 18:21:11,692][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.14%, Current % of VRAM taken: 60.49%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 18:21:12,414][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:21:12,416][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:21:12,417][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:21:13,096][__main__][INFO] - Iteration 117 took 1m 13s (8.76% Gen, 90.32% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 52m 2s. Estimated total time: 61h 38m 2s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 16s, 500 more iterations: 10h 16m 20s. [2026-03-25 18:21:13,098][__main__][INFO] - Starting iteration 117. [2026-03-25 18:21:13,499][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:21:13,500][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:21:16,918][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:21:19,975][__main__][INFO] - Number of regex retries in iteration 117: 1 [2026-03-25 18:21:19,976][__main__][INFO] - agents played in iteration 117 are Bob, Alice [2026-03-25 18:21:20,933][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:21:21,776][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:21:22,231][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:21:22,736][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:21:23,237][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:21:23,737][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:21:24,238][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:21:24,738][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:21:25,239][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:21:25,739][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:21:26,241][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:21:26,742][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:21:27,242][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:21:27,742][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:21:28,241][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:21:28,741][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:21:29,242][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:21:29,742][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:21:30,244][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:21:30,746][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:21:31,247][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:21:31,748][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:21:32,248][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:21:32,749][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:21:33,249][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:21:33,750][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:21:34,250][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:21:34,749][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:21:35,248][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:21:35,747][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:21:36,247][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:21:36,746][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:21:37,246][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:21:37,746][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:21:38,246][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:21:38,745][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:21:39,244][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:21:39,744][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:21:40,244][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:21:40,743][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:21:41,244][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:21:41,745][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:21:42,245][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:21:42,744][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:21:43,243][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:21:43,743][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:21:44,244][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:21:44,745][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:21:45,245][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:21:45,745][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:21:46,245][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:21:46,745][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:21:47,246][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:21:47,747][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:21:48,248][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:21:48,748][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:21:49,248][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:21:49,748][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:21:50,248][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:21:50,747][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:21:51,248][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:21:51,747][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:21:52,247][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:21:52,747][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:21:53,247][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:21:53,746][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:21:54,246][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:21:54,745][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:21:55,244][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:21:55,744][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:21:56,244][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:21:56,744][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:21:57,243][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:21:57,742][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:21:58,242][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:21:58,742][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:21:59,243][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:21:59,742][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:22:00,243][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:22:00,743][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:22:01,244][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:22:01,744][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:22:02,246][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:22:02,747][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:22:03,248][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:22:03,748][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:22:04,249][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:22:04,750][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:22:05,250][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:22:05,751][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:22:06,251][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:22:06,750][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:22:07,252][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:22:07,752][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:22:08,251][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:22:08,750][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:22:09,250][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:22:09,750][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:22:10,249][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:22:10,748][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:22:11,248][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:22:11,749][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:22:12,250][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:22:12,749][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:22:13,248][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:22:13,747][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:22:14,247][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:22:14,747][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:22:15,246][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:22:15,746][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:22:16,245][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:22:16,744][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:22:17,243][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:22:17,743][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:22:18,243][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:22:18,745][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:22:19,245][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:22:19,746][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:22:20,248][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:22:20,748][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:22:21,249][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:22:21,750][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:22:22,250][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:22:22,750][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:22:23,250][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:22:23,750][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:22:24,250][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:22:24,749][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:22:25,249][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:22:25,748][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 18:22:26,361][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 18:22:27,083][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:22:27,085][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:22:27,087][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:22:27,777][__main__][INFO] - Iteration 118 took 1m 14s (8.72% Gen, 90.35% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 6m 40s. Estimated total time: 61h 53m 54s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 47s, 500 more iterations: 10h 18m 59s. [2026-03-25 18:22:27,780][__main__][INFO] - Starting iteration 118. [2026-03-25 18:22:28,185][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:22:28,186][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:22:34,374][__main__][INFO] - Number of regex retries in iteration 118: 0 [2026-03-25 18:22:34,375][__main__][INFO] - agents played in iteration 118 are Bob, Alice [2026-03-25 18:22:35,353][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:22:35,933][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:22:36,390][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:22:36,896][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:22:37,396][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:22:37,897][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:22:38,398][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:22:38,901][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:22:39,403][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:22:39,904][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:22:40,405][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:22:40,906][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:22:41,407][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:22:41,908][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:22:42,408][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:22:42,908][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:22:43,408][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:22:43,908][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:22:44,409][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:22:44,910][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:22:45,413][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:22:45,914][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:22:46,415][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:22:46,916][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:22:47,417][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:22:47,917][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:22:48,417][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:22:48,918][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:22:49,419][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:22:49,919][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:22:50,419][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:22:50,919][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:22:51,419][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:22:51,920][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:22:52,422][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:22:52,923][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:22:53,424][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:22:53,925][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:22:54,425][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:22:54,926][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:22:55,426][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:22:55,928][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:22:56,428][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:22:56,928][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:22:57,427][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:22:57,928][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:22:58,427][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:22:58,927][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:22:59,427][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:22:59,927][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:23:00,431][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:23:00,932][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:23:01,433][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:23:01,935][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:23:02,437][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:23:02,938][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:23:03,440][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:23:03,943][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:23:04,443][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:23:04,943][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:23:05,443][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:23:05,944][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:23:06,445][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:23:06,945][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:23:07,445][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:23:07,946][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:23:08,447][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:23:08,949][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:23:09,450][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:23:09,951][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:23:10,451][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:23:10,952][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:23:11,454][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:23:11,956][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:23:12,455][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:23:12,955][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:23:13,454][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:23:13,953][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:23:14,452][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:23:14,952][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:23:15,451][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:23:15,951][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:23:16,451][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:23:16,952][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:23:17,452][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:23:17,952][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:23:18,453][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:23:18,953][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:23:19,454][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:23:19,954][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:23:20,455][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:23:20,955][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:23:21,454][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:23:21,954][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:23:22,454][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:23:22,954][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:23:23,454][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:23:23,956][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:23:24,456][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:23:24,956][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:23:25,457][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:23:25,957][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:23:26,457][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:23:26,958][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:23:27,459][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:23:27,958][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:23:28,458][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:23:28,958][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:23:29,457][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:23:29,957][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:23:30,455][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:23:30,956][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:23:31,455][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:23:31,954][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:23:32,455][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:23:32,956][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:23:33,458][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:23:33,959][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:23:34,461][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:23:34,962][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:23:35,464][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:23:35,966][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:23:36,467][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:23:36,968][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:23:37,469][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:23:37,969][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:23:38,470][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:23:38,971][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:23:39,471][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:23:39,971][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21719 tokens. [2026-03-25 18:23:40,585][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.36%, ΔTime: 00:01:04 [2026-03-25 18:23:41,311][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:23:41,314][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:23:41,315][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:23:41,938][__main__][INFO] - Iteration 119 took 1m 13s (8.39% Gen, 90.76% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 39m 10s. Estimated total time: 61h 27m 38s. Time estimates for 10 more iterations: 12m 17s, 100 more iterations: 2h 2m 55s, 500 more iterations: 10h 14m 36s. [2026-03-25 18:23:41,940][__main__][INFO] - Starting iteration 119. [2026-03-25 18:23:42,341][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:23:42,342][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:23:48,660][__main__][INFO] - Number of regex retries in iteration 119: 0 [2026-03-25 18:23:48,660][__main__][INFO] - agents played in iteration 119 are Bob, Alice [2026-03-25 18:23:49,612][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:23:50,187][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:23:50,644][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:23:51,148][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:23:51,649][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:23:52,150][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:23:52,651][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:23:53,151][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:23:53,651][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:23:54,151][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:23:54,650][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:23:55,150][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:23:55,649][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:23:56,148][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:23:56,647][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:23:57,146][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:23:57,645][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:23:58,145][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:23:58,646][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:23:59,146][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:23:59,646][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:24:00,142][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:24:00,642][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:24:01,142][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:24:01,642][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:24:02,142][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:24:02,642][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:24:03,142][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:24:03,640][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:24:04,139][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:24:04,637][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:24:05,136][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:24:05,635][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:24:06,134][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:24:06,637][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:24:07,139][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:24:07,641][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:24:08,143][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:24:08,644][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:24:09,146][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:24:09,647][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:24:10,149][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:24:10,648][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:24:11,147][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:24:11,648][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:24:12,147][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:24:12,647][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:24:13,145][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:24:13,644][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:24:14,143][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:24:14,644][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:24:15,145][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:24:15,645][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:24:16,146][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:24:16,646][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:24:17,147][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:24:17,647][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:24:18,148][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:24:18,648][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:24:19,148][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:24:19,649][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:24:20,148][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:24:20,648][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:24:21,148][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:24:21,648][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:24:22,148][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:24:22,648][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:24:23,149][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:24:23,650][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:24:24,151][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:24:24,650][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:24:25,151][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:24:25,651][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:24:26,151][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:24:26,650][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:24:27,149][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:24:27,648][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:24:28,147][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:24:28,647][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:24:29,147][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:24:29,646][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:24:30,145][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:24:30,645][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:24:31,145][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:24:31,644][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:24:32,145][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:24:32,645][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:24:33,145][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:24:33,645][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:24:34,145][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:24:34,644][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:24:35,143][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:24:35,643][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:24:36,143][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:24:36,644][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:24:37,144][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:24:37,643][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:24:38,143][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:24:38,645][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:24:39,146][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:24:39,647][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:24:40,149][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:24:40,651][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:24:41,153][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:24:41,657][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:24:42,160][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:24:42,660][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:24:43,162][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:24:43,661][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:24:44,162][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:24:44,662][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:24:45,160][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:24:45,659][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:24:46,161][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:24:46,662][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:24:47,163][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:24:47,663][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:24:48,165][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:24:48,665][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:24:49,165][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:24:49,666][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:24:50,167][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:24:50,668][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:24:51,168][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:24:51,668][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:24:52,167][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:24:52,668][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:24:53,168][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:24:53,668][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:24:54,169][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21718 tokens. [2026-03-25 18:24:54,778][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-25 18:24:55,506][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:24:55,510][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:24:55,512][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:24:56,153][__main__][INFO] - Iteration 120 took 1m 13s (8.56% Gen, 90.57% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 40m 53s. Estimated total time: 61h 30m 35s. Time estimates for 10 more iterations: 12m 18s, 100 more iterations: 2h 3m 1s, 500 more iterations: 10h 15m 5s. [2026-03-25 18:24:56,156][__main__][INFO] - Starting iteration 120. [2026-03-25 18:24:56,562][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:24:56,563][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:25:02,740][__main__][INFO] - Number of regex retries in iteration 120: 0 [2026-03-25 18:25:02,741][__main__][INFO] - agents played in iteration 120 are Bob, Alice [2026-03-25 18:25:03,723][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:25:04,559][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:25:05,015][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:25:05,519][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:25:06,018][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:25:06,516][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:25:07,016][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:25:07,516][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:25:08,015][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:25:08,515][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:25:09,017][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:25:09,519][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:25:10,018][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:25:10,520][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:25:11,021][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:25:11,524][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:25:12,026][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:25:12,526][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:25:13,026][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:25:13,525][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:25:14,024][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:25:14,523][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:25:15,023][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:25:15,523][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:25:16,022][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:25:16,521][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:25:17,022][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:25:17,523][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:25:18,023][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:25:18,524][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:25:19,024][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:25:19,524][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:25:20,025][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:25:20,525][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:25:21,026][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:25:21,526][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:25:22,027][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:25:22,528][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:25:23,029][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:25:23,530][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:25:24,031][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:25:24,531][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:25:25,034][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:25:25,535][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:25:26,036][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:25:26,536][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:25:27,036][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:25:27,537][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:25:28,039][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:25:28,540][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:25:29,038][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:25:29,537][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:25:30,035][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:25:30,533][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:25:31,031][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:25:31,530][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:25:32,028][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:25:32,527][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:25:33,027][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:25:33,527][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:25:34,028][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:25:34,528][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:25:35,028][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:25:35,529][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:25:36,029][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:25:36,529][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:25:37,028][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:25:37,528][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:25:38,027][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:25:38,527][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:25:39,026][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:25:39,525][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:25:40,025][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:25:40,525][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:25:41,025][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:25:41,529][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:25:42,029][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:25:42,530][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:25:43,031][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:25:43,532][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:25:44,032][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:25:44,532][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:25:45,032][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:25:45,531][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:25:46,031][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:25:46,530][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:25:47,031][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:25:47,531][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:25:48,031][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:25:48,532][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:25:49,033][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:25:49,534][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:25:50,034][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:25:50,534][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:25:51,035][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:25:51,534][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:25:52,034][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:25:52,534][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:25:53,034][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:25:53,535][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:25:54,035][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:25:54,535][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:25:55,035][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:25:55,535][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:25:56,034][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:25:56,535][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:25:57,035][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:25:57,533][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:25:58,032][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:25:58,530][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:25:59,031][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:25:59,529][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:26:00,031][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:26:00,529][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:26:01,028][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:26:01,527][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:26:02,026][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:26:02,526][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:26:03,024][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:26:03,523][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:26:04,022][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:26:04,522][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:26:05,021][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:26:05,522][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:26:06,022][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:26:06,523][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:26:07,023][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:26:07,523][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:26:08,023][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:26:08,523][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21633 tokens. [2026-03-25 18:26:09,134][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-25 18:26:09,857][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:26:09,859][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:26:09,860][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:26:10,492][__main__][INFO] - Iteration 121 took 1m 13s (8.36% Gen, 90.79% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 58h 45m 33s. Estimated total time: 61h 36m 30s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 13s, 500 more iterations: 10h 16m 5s. [2026-03-25 18:26:10,494][__main__][INFO] - Starting iteration 121. [2026-03-25 18:26:10,897][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:26:10,897][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:26:13,980][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:26:17,213][__main__][INFO] - Number of regex retries in iteration 121: 1 [2026-03-25 18:26:17,214][__main__][INFO] - agents played in iteration 121 are Bob, Alice [2026-03-25 18:26:18,171][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:26:18,747][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:26:19,205][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:26:19,711][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:26:20,212][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:26:20,713][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:26:21,214][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:26:21,716][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:26:22,217][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:26:22,719][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:26:23,222][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:26:23,725][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:26:24,228][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:26:24,730][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:26:25,231][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:26:25,733][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:26:26,235][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:26:26,737][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:26:27,237][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:26:27,737][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:26:28,237][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:26:28,737][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:26:29,238][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:26:29,737][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:26:30,236][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:26:30,735][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:26:31,236][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:26:31,738][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:26:32,239][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:26:32,740][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:26:33,241][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:26:33,742][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:26:34,244][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:26:34,745][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:26:35,246][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:26:35,746][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:26:36,247][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:26:36,748][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:26:37,249][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:26:37,750][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:26:38,252][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:26:38,752][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:26:39,252][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:26:39,751][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:26:40,250][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:26:40,750][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:26:41,252][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:26:41,753][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:26:42,253][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:26:42,753][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:26:43,252][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:26:43,752][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:26:44,252][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:26:44,751][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:26:45,251][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:26:45,750][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:26:46,250][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:26:46,749][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:26:47,249][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:26:47,750][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:26:48,251][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:26:48,752][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:26:49,253][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:26:49,756][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:26:50,257][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:26:50,758][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:26:51,260][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:26:51,762][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:26:52,263][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:26:52,765][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:26:53,265][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:26:53,767][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:26:54,268][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:26:54,770][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:26:55,271][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:26:55,773][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:26:56,274][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:26:56,775][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:26:57,277][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:26:57,779][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:26:58,280][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:26:58,782][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:26:59,284][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:26:59,785][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:27:00,286][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:27:00,786][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:27:01,287][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:27:01,787][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:27:02,288][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:27:02,789][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:27:03,290][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:27:03,791][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:27:04,293][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:27:04,793][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:27:05,294][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:27:05,795][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:27:06,296][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:27:06,797][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:27:07,298][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:27:07,799][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:27:08,299][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:27:08,800][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:27:09,302][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:27:09,803][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:27:10,304][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:27:10,806][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:27:11,307][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:27:11,809][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:27:12,308][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:27:12,808][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:27:13,308][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:27:13,808][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:27:14,308][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:27:14,808][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:27:15,308][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:27:15,809][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:27:16,309][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:27:16,809][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:27:17,308][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:27:17,809][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:27:18,308][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:27:18,808][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:27:19,309][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:27:19,811][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:27:20,312][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:27:20,814][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:27:21,315][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:27:21,816][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:27:22,317][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:27:22,819][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 18:27:23,427][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.50%, ΔTime: 00:01:04 [2026-03-25 18:27:24,149][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:27:24,151][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:27:24,153][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:27:24,787][__main__][INFO] - Iteration 122 took 1m 13s (8.55% Gen, 90.59% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 42m 19s. Estimated total time: 61h 34m 30s. Time estimates for 10 more iterations: 12m 18s, 100 more iterations: 2h 3m 9s, 500 more iterations: 10h 15m 45s. [2026-03-25 18:27:24,789][__main__][INFO] - Starting iteration 122. [2026-03-25 18:27:25,191][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:27:25,191][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:27:28,059][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:27:31,002][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:27:32,076][__main__][INFO] - Number of regex retries in iteration 122: 2 [2026-03-25 18:27:32,077][__main__][INFO] - agents played in iteration 122 are Bob, Alice [2026-03-25 18:27:33,058][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:27:33,636][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:27:34,095][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:27:34,600][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:27:35,101][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:27:35,602][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:27:36,103][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:27:36,599][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:27:37,102][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:27:37,603][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:27:38,102][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:27:38,602][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:27:39,100][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:27:39,600][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:27:40,100][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:27:40,602][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:27:41,103][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:27:41,604][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:27:42,108][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:27:42,611][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:27:43,114][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:27:43,617][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:27:44,120][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:27:44,623][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:27:45,126][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:27:45,629][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:27:46,128][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:27:46,628][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:27:47,128][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:27:47,629][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:27:48,129][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:27:48,629][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:27:49,129][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:27:49,629][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:27:50,128][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:27:50,628][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:27:51,128][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:27:51,629][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:27:52,129][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:27:52,629][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:27:53,130][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:27:53,629][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:27:54,129][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:27:54,628][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:27:55,128][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:27:55,628][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:27:56,128][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:27:56,628][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:27:57,128][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:27:57,628][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:27:58,127][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:27:58,627][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:27:59,127][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:27:59,627][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:28:00,127][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:28:00,626][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:28:01,125][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:28:01,624][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:28:02,124][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:28:02,624][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:28:03,125][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:28:03,625][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:28:04,125][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:28:04,625][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:28:05,125][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:28:05,625][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:28:06,125][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:28:06,625][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:28:07,126][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:28:07,626][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:28:08,126][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:28:08,626][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:28:09,126][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:28:09,626][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:28:10,125][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:28:10,624][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:28:11,124][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:28:11,625][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:28:12,125][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:28:12,625][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:28:13,124][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:28:13,624][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:28:14,126][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:28:14,630][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:28:15,133][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:28:15,635][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:28:16,138][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:28:16,639][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:28:17,142][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:28:17,645][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:28:18,145][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:28:18,645][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:28:19,145][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:28:19,645][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:28:20,144][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:28:20,644][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:28:21,144][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:28:21,644][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:28:22,144][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:28:22,643][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:28:23,144][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:28:23,643][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:28:24,143][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:28:24,643][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:28:25,143][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:28:25,643][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:28:26,142][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:28:26,642][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:28:27,140][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:28:27,642][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:28:28,142][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:28:28,641][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:28:29,141][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:28:29,640][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:28:30,138][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:28:30,636][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:28:31,135][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:28:31,633][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:28:32,132][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:28:32,631][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:28:33,130][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:28:33,629][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:28:34,129][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:28:34,629][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:28:35,128][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:28:35,627][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:28:36,127][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:28:36,627][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:28:37,127][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:28:37,627][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21705 tokens. [2026-03-25 18:28:38,238][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:04 [2026-03-25 18:28:38,973][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:28:38,976][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:28:38,977][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:28:39,634][__main__][INFO] - Iteration 123 took 1m 14s (9.25% Gen, 89.87% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 59h 8m 46s. Estimated total time: 62h 2m 12s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 4s, 500 more iterations: 10h 20m 22s. [2026-03-25 18:28:39,637][__main__][INFO] - Starting iteration 123. [2026-03-25 18:28:40,039][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:28:40,039][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:28:41,626][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:28:46,479][__main__][INFO] - Number of regex retries in iteration 123: 1 [2026-03-25 18:28:46,480][__main__][INFO] - agents played in iteration 123 are Bob, Alice [2026-03-25 18:28:47,438][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:28:48,016][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:28:48,474][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:28:48,981][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:28:49,484][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:28:49,986][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:28:50,488][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:28:50,990][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:28:51,491][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:28:51,993][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:28:52,494][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:28:52,995][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:28:53,496][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:28:53,996][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:28:54,498][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:28:54,999][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:28:55,503][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:28:56,003][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:28:56,505][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:28:57,006][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:28:57,507][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:28:58,008][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:28:58,509][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:28:59,010][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:28:59,511][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:29:00,012][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:29:00,510][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:29:01,009][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:29:01,508][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:29:02,007][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:29:02,506][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:29:03,005][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:29:03,504][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:29:04,004][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:29:04,506][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:29:05,007][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:29:05,508][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:29:06,009][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:29:06,511][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:29:07,012][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:29:07,512][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:29:08,013][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:29:08,514][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:29:09,014][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:29:09,516][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:29:10,017][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:29:10,518][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:29:11,019][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:29:11,521][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:29:12,023][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:29:12,524][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:29:13,024][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:29:13,525][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:29:14,025][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:29:14,526][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:29:15,026][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:29:15,526][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:29:16,026][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:29:16,527][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:29:17,028][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:29:17,528][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:29:18,029][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:29:18,529][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:29:19,029][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:29:19,530][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:29:20,030][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:29:20,533][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:29:21,034][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:29:21,536][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:29:22,037][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:29:22,540][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:29:23,041][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:29:23,543][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:29:24,045][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:29:24,545][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:29:25,045][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:29:25,546][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:29:26,047][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:29:26,547][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:29:27,047][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:29:27,548][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:29:28,048][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:29:28,549][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:29:29,050][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:29:29,551][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:29:30,051][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:29:30,551][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:29:31,051][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:29:31,551][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:29:32,051][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:29:32,549][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:29:33,048][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:29:33,547][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:29:34,045][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:29:34,544][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:29:35,042][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:29:35,541][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:29:36,040][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:29:36,543][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:29:37,045][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:29:37,547][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:29:38,048][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:29:38,550][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:29:39,051][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:29:39,553][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:29:40,054][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:29:40,556][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:29:41,056][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:29:41,560][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:29:42,062][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:29:42,564][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:29:43,065][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:29:43,565][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:29:44,066][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:29:44,566][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:29:45,066][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:29:45,566][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:29:46,066][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:29:46,566][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:29:47,066][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:29:47,566][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:29:48,066][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:29:48,566][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:29:49,066][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:29:49,567][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:29:50,067][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:29:50,568][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:29:51,068][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:29:51,568][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:29:52,068][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 18:29:52,676][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 18:29:53,402][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:29:53,404][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:29:53,406][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:29:54,193][__main__][INFO] - Iteration 124 took 1m 14s (8.69% Gen, 90.25% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 53m 4s. Estimated total time: 61h 47m 45s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 35s, 500 more iterations: 10h 17m 57s. [2026-03-25 18:29:54,195][__main__][INFO] - Starting iteration 124. [2026-03-25 18:29:54,600][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:29:54,600][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:30:01,220][__main__][INFO] - Number of regex retries in iteration 124: 0 [2026-03-25 18:30:01,221][__main__][INFO] - agents played in iteration 124 are Bob, Alice [2026-03-25 18:30:02,205][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:30:02,788][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:30:03,246][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:30:03,751][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:30:04,253][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:30:04,754][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:30:05,256][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:30:05,757][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:30:06,258][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:30:06,761][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:30:07,263][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:30:07,765][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:30:08,266][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:30:08,768][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:30:09,269][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:30:09,771][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:30:10,272][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:30:10,775][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:30:11,280][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:30:11,786][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:30:12,289][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:30:12,792][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:30:13,296][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:30:13,799][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:30:14,302][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:30:14,806][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:30:15,308][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:30:15,807][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:30:16,310][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:30:16,811][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:30:17,312][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:30:17,813][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:30:18,315][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:30:18,816][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:30:19,318][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:30:19,821][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:30:20,323][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:30:20,825][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:30:21,328][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:30:21,830][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:30:22,332][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:30:22,833][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:30:23,337][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:30:23,843][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:30:24,346][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:30:24,849][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:30:25,352][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:30:25,855][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:30:26,359][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:30:26,863][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:30:27,366][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:30:27,867][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:30:28,369][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:30:28,870][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:30:29,372][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:30:29,874][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:30:30,375][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:30:30,876][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:30:31,377][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:30:31,878][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:30:32,382][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:30:32,884][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:30:33,385][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:30:33,887][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:30:34,389][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:30:34,890][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:30:35,391][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:30:35,893][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:30:36,395][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:30:36,893][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:30:37,394][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:30:37,895][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:30:38,398][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:30:38,901][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:30:39,400][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:30:39,903][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:30:40,405][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:30:40,908][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:30:41,413][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:30:41,915][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:30:42,418][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:30:42,920][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:30:43,422][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:30:43,924][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:30:44,427][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:30:44,930][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:30:45,432][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:30:45,934][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:30:46,437][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:30:46,940][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:30:47,442][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:30:47,943][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:30:48,444][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:30:48,944][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:30:49,445][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:30:49,947][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:30:50,448][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:30:50,950][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:30:51,451][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:30:51,952][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:30:52,452][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:30:52,953][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:30:53,454][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:30:53,954][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:30:54,456][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:30:54,957][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:30:55,460][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:30:55,964][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:30:56,467][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:30:56,969][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:30:57,471][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:30:57,974][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:30:58,476][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:30:58,978][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:30:59,481][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:30:59,983][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:31:00,484][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:31:00,985][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:31:01,486][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:31:01,987][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:31:02,488][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:31:02,989][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:31:03,490][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:31:03,990][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:31:04,491][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:31:04,992][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:31:05,494][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:31:05,995][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:31:06,498][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:31:07,000][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21628 tokens. [2026-03-25 18:31:07,618][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:04 [2026-03-25 18:31:08,352][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:31:08,354][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:31:08,355][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:31:09,000][__main__][INFO] - Iteration 125 took 1m 14s (8.90% Gen, 90.23% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 4m 5s. Estimated total time: 62h 0m 1s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 0s, 500 more iterations: 10h 20m 0s. [2026-03-25 18:31:09,001][__main__][INFO] - Starting iteration 125. [2026-03-25 18:31:09,404][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:31:09,404][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:31:10,007][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:31:16,059][__main__][INFO] - Number of regex retries in iteration 125: 1 [2026-03-25 18:31:16,060][__main__][INFO] - agents played in iteration 125 are Bob, Alice [2026-03-25 18:31:17,016][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:31:17,598][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:31:18,056][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:31:18,562][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:31:19,064][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:31:19,565][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:31:20,067][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:31:20,568][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:31:21,069][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:31:21,570][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:31:22,071][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:31:22,573][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:31:23,073][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:31:23,575][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:31:24,077][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:31:24,578][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:31:25,079][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:31:25,582][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:31:26,086][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:31:26,589][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:31:27,091][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:31:27,594][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:31:28,097][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:31:28,602][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:31:29,105][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:31:29,609][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:31:30,111][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:31:30,613][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:31:31,114][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:31:31,616][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:31:32,118][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:31:32,620][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:31:33,121][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:31:33,624][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:31:34,125][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:31:34,628][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:31:35,129][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:31:35,632][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:31:36,133][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:31:36,634][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:31:37,136][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:31:37,637][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:31:38,140][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:31:38,643][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:31:39,146][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:31:39,648][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:31:40,151][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:31:40,654][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:31:41,157][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:31:41,661][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:31:42,163][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:31:42,664][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:31:43,165][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:31:43,665][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:31:44,167][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:31:44,668][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:31:45,169][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:31:45,670][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:31:46,171][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:31:46,672][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:31:47,173][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:31:47,674][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:31:48,174][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:31:48,673][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:31:49,174][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:31:49,675][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:31:50,177][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:31:50,677][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:31:51,180][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:31:51,682][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:31:52,184][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:31:52,686][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:31:53,188][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:31:53,689][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:31:54,190][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:31:54,690][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:31:55,190][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:31:55,691][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:31:56,193][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:31:56,693][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:31:57,195][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:31:57,697][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:31:58,202][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:31:58,705][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:31:59,209][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:31:59,712][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:32:00,214][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:32:00,717][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:32:01,221][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:32:01,725][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:32:02,227][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:32:02,729][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:32:03,231][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:32:03,732][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:32:04,234][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:32:04,735][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:32:05,237][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:32:05,738][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:32:06,239][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:32:06,742][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:32:07,244][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:32:07,746][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:32:08,248][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:32:08,750][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:32:09,252][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:32:09,753][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:32:10,255][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:32:10,758][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:32:11,262][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:32:11,766][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:32:12,269][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:32:12,771][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:32:13,274][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:32:13,776][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:32:14,277][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:32:14,777][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:32:15,278][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:32:15,779][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:32:16,281][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:32:16,783][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:32:17,284][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:32:17,786][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:32:18,286][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:32:18,787][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:32:19,288][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:32:19,789][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:32:20,290][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:32:20,791][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:32:21,291][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:32:21,792][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 18:32:22,407][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-25 18:32:23,139][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:32:23,141][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:32:23,142][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:32:23,784][__main__][INFO] - Iteration 126 took 1m 14s (8.95% Gen, 90.19% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 1m 53s. Estimated total time: 61h 59m 3s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 58s, 500 more iterations: 10h 19m 50s. [2026-03-25 18:32:23,786][__main__][INFO] - Starting iteration 126. [2026-03-25 18:32:24,192][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:32:24,193][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:32:30,336][__main__][INFO] - Number of regex retries in iteration 126: 0 [2026-03-25 18:32:30,337][__main__][INFO] - agents played in iteration 126 are Bob, Alice [2026-03-25 18:32:31,304][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:32:31,890][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:32:32,344][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:32:32,850][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:32:33,350][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:32:33,850][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:32:34,349][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:32:34,849][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:32:35,347][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:32:35,847][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:32:36,351][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:32:36,853][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:32:37,356][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:32:37,857][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:32:38,357][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:32:38,858][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:32:39,362][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:32:39,863][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:32:40,365][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:32:40,866][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:32:41,369][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:32:41,870][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:32:42,372][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:32:42,873][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:32:43,374][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:32:43,875][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:32:44,376][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:32:44,877][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:32:45,377][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:32:45,878][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:32:46,380][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:32:46,880][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:32:47,381][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:32:47,882][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:32:48,383][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:32:48,884][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:32:49,384][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:32:49,885][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:32:50,385][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:32:50,885][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:32:51,386][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:32:51,886][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:32:52,389][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:32:52,891][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:32:53,392][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:32:53,892][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:32:54,393][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:32:54,894][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:32:55,394][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:32:55,895][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:32:56,396][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:32:56,896][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:32:57,397][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:32:57,898][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:32:58,399][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:32:58,901][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:32:59,402][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:32:59,903][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:33:00,405][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:33:00,907][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:33:01,408][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:33:01,910][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:33:02,412][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:33:02,913][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:33:03,414][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:33:03,914][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:33:04,413][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:33:04,912][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:33:05,410][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:33:05,910][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:33:06,409][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:33:06,909][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:33:07,408][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:33:07,908][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:33:08,411][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:33:08,912][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:33:09,414][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:33:09,915][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:33:10,416][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:33:10,917][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:33:11,422][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:33:11,924][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:33:12,426][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:33:12,927][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:33:13,429][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:33:13,930][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:33:14,432][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:33:14,933][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:33:15,434][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:33:15,935][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:33:16,436][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:33:16,936][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:33:17,436][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:33:17,937][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:33:18,438][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:33:18,939][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:33:19,439][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:33:19,940][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:33:20,440][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:33:20,941][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:33:21,443][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:33:21,943][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:33:22,444][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:33:22,944][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:33:23,445][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:33:23,946][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:33:24,447][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:33:24,948][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:33:25,449][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:33:25,949][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:33:26,450][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:33:26,951][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:33:27,452][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:33:27,952][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:33:28,454][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:33:28,955][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:33:29,455][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:33:29,956][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:33:30,457][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:33:30,957][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:33:31,458][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:33:31,959][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:33:32,459][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:33:32,960][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:33:33,460][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:33:33,963][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:33:34,464][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:33:34,965][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:33:35,466][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:33:35,967][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 18:33:36,585][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.20%, ΔTime: 00:01:04 [2026-03-25 18:33:37,312][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:33:37,315][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:33:37,316][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:33:37,959][__main__][INFO] - Iteration 127 took 1m 13s (8.33% Gen, 90.80% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 29m 56s. Estimated total time: 61h 28m 21s. Time estimates for 10 more iterations: 12m 17s, 100 more iterations: 2h 2m 56s, 500 more iterations: 10h 14m 43s. [2026-03-25 18:33:37,961][__main__][INFO] - Starting iteration 127. [2026-03-25 18:33:38,362][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:33:38,363][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:33:44,628][__main__][INFO] - Number of regex retries in iteration 127: 0 [2026-03-25 18:33:44,628][__main__][INFO] - agents played in iteration 127 are Bob, Alice [2026-03-25 18:33:45,588][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:33:46,172][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:33:46,629][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:33:47,136][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:33:47,638][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:33:48,140][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:33:48,642][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:33:49,144][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:33:49,646][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:33:50,149][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:33:50,650][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:33:51,150][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:33:51,651][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:33:52,151][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:33:52,652][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:33:53,153][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:33:53,653][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:33:54,153][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:33:54,655][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:33:55,155][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:33:55,655][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:33:56,156][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:33:56,656][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:33:57,157][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:33:57,658][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:33:58,159][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:33:58,659][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:33:59,162][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:33:59,661][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:34:00,163][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:34:00,664][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:34:01,164][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:34:01,665][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:34:02,165][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:34:02,665][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:34:03,165][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:34:03,665][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:34:04,165][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:34:04,665][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:34:05,165][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:34:05,665][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:34:06,165][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:34:06,667][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:34:07,169][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:34:07,670][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:34:08,171][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:34:08,671][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:34:09,171][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:34:09,672][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:34:10,172][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:34:10,672][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:34:11,173][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:34:11,674][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:34:12,173][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:34:12,672][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:34:13,172][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:34:13,672][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:34:14,172][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:34:14,673][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:34:15,172][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:34:15,672][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:34:16,173][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:34:16,673][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:34:17,174][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:34:17,674][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:34:18,175][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:34:18,675][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:34:19,175][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:34:19,676][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:34:20,178][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:34:20,678][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:34:21,178][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:34:21,680][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:34:22,181][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:34:22,683][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:34:23,183][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:34:23,684][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:34:24,183][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:34:24,684][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:34:25,184][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:34:25,684][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:34:26,185][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:34:26,685][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:34:27,185][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:34:27,686][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:34:28,187][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:34:28,687][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:34:29,187][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:34:29,688][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:34:30,189][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:34:30,689][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:34:31,189][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:34:31,689][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:34:32,189][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:34:32,689][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:34:33,189][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:34:33,690][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:34:34,190][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:34:34,690][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:34:35,190][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:34:35,689][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:34:36,189][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:34:36,689][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:34:37,188][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:34:37,688][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:34:38,189][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:34:38,690][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:34:39,190][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:34:39,691][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:34:40,192][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:34:40,693][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:34:41,195][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:34:41,698][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:34:42,200][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:34:42,703][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:34:43,204][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:34:43,704][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:34:44,204][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:34:44,704][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:34:45,205][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:34:45,706][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:34:46,206][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:34:46,707][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:34:47,208][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:34:47,709][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:34:48,210][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:34:48,710][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:34:49,211][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:34:49,711][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:34:50,212][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21729 tokens. [2026-03-25 18:34:50,829][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:04 [2026-03-25 18:34:51,562][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:34:51,564][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:34:51,565][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:34:52,408][__main__][INFO] - Iteration 128 took 1m 14s (8.46% Gen, 90.40% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 42m 40s. Estimated total time: 61h 42m 19s. Time estimates for 10 more iterations: 12m 20s, 100 more iterations: 2h 3m 24s, 500 more iterations: 10h 17m 3s. [2026-03-25 18:34:52,410][__main__][INFO] - Starting iteration 128. [2026-03-25 18:34:52,818][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:34:52,819][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:34:59,062][__main__][INFO] - Number of regex retries in iteration 128: 0 [2026-03-25 18:34:59,063][__main__][INFO] - agents played in iteration 128 are Bob, Alice [2026-03-25 18:35:00,297][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:35:00,874][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:35:01,334][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:35:01,841][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:35:02,343][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:35:02,844][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:35:03,346][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:35:03,847][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:35:04,349][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:35:04,850][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:35:05,350][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:35:05,851][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:35:06,351][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:35:06,851][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:35:07,351][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:35:07,852][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:35:08,352][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:35:08,852][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:35:09,354][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:35:09,854][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:35:10,354][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:35:10,855][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:35:11,357][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:35:11,858][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:35:12,359][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:35:12,859][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:35:13,362][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:35:13,863][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:35:14,364][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:35:14,864][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:35:15,366][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:35:15,867][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:35:16,368][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:35:16,868][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:35:17,368][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:35:17,869][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:35:18,369][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:35:18,869][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:35:19,369][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:35:19,869][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:35:20,369][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:35:20,869][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:35:21,369][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:35:21,870][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:35:22,370][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:35:22,869][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:35:23,369][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:35:23,869][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:35:24,370][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:35:24,870][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:35:25,371][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:35:25,871][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:35:26,371][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:35:26,871][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:35:27,371][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:35:27,872][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:35:28,372][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:35:28,873][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:35:29,373][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:35:29,873][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:35:30,374][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:35:30,874][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:35:31,375][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:35:31,875][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:35:32,376][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:35:32,877][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:35:33,379][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:35:33,880][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:35:34,382][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:35:34,883][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:35:35,384][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:35:35,886][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:35:36,387][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:35:36,889][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:35:37,391][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:35:37,891][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:35:38,391][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:35:38,891][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:35:39,390][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:35:39,890][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:35:40,391][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:35:40,891][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:35:41,393][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:35:41,894][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:35:42,395][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:35:42,897][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:35:43,398][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:35:43,901][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:35:44,403][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:35:44,904][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:35:45,406][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:35:45,908][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:35:46,409][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:35:46,912][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:35:47,413][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:35:47,915][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:35:48,416][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:35:48,918][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:35:49,419][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:35:49,921][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:35:50,421][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:35:50,921][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:35:51,421][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:35:51,921][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:35:52,423][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:35:52,923][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:35:53,424][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:35:53,923][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:35:54,423][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:35:54,924][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:35:55,423][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:35:55,925][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:35:56,426][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:35:56,926][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:35:57,428][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:35:57,929][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:35:58,430][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:35:58,931][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:35:59,432][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:35:59,932][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:36:00,433][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:36:00,935][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:36:01,435][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:36:01,937][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:36:02,439][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:36:02,941][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:36:03,441][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:36:03,942][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:36:04,444][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:36:04,945][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 18:36:05,554][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:04 [2026-03-25 18:36:06,291][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:36:06,293][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:36:06,295][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:36:07,240][__main__][INFO] - Iteration 129 took 1m 14s (8.39% Gen, 90.34% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 0m 11s. Estimated total time: 62h 1m 5s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 2s, 500 more iterations: 10h 20m 10s. [2026-03-25 18:36:07,241][__main__][INFO] - Starting iteration 129. [2026-03-25 18:36:07,640][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:36:07,640][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:36:13,787][__main__][INFO] - Number of regex retries in iteration 129: 0 [2026-03-25 18:36:13,788][__main__][INFO] - agents played in iteration 129 are Bob, Alice [2026-03-25 18:36:14,752][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:36:15,331][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:36:15,790][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:36:16,297][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:36:16,800][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:36:17,304][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:36:17,807][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:36:18,310][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:36:18,813][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:36:19,316][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:36:19,818][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:36:20,320][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:36:20,823][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:36:21,324][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:36:21,827][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:36:22,329][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:36:22,831][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:36:23,333][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:36:23,836][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:36:24,338][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:36:24,841][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:36:25,344][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:36:25,844][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:36:26,345][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:36:26,846][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:36:27,347][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:36:27,849][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:36:28,351][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:36:28,852][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:36:29,355][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:36:29,855][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:36:30,357][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:36:30,858][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:36:31,360][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:36:31,861][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:36:32,362][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:36:32,863][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:36:33,364][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:36:33,864][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:36:34,365][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:36:34,866][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:36:35,366][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:36:35,868][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:36:36,368][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:36:36,870][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:36:37,370][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:36:37,872][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:36:38,373][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:36:38,874][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:36:39,374][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:36:39,877][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:36:40,379][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:36:40,881][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:36:41,385][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:36:41,888][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:36:42,389][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:36:42,891][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:36:43,392][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:36:43,894][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:36:44,395][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:36:44,895][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:36:45,395][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:36:45,896][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:36:46,397][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:36:46,898][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:36:47,399][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:36:47,901][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:36:48,403][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:36:48,906][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:36:49,410][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:36:49,913][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:36:50,415][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:36:50,917][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:36:51,417][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:36:51,919][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:36:52,421][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:36:52,922][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:36:53,424][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:36:53,925][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:36:54,426][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:36:54,928][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:36:55,430][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:36:55,931][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:36:56,432][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:36:56,933][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:36:57,434][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:36:57,934][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:36:58,435][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:36:58,936][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:36:59,437][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:36:59,938][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:37:00,439][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:37:00,940][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:37:01,442][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:37:01,944][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:37:02,446][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:37:02,947][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:37:03,449][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:37:03,949][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:37:04,450][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:37:04,950][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:37:05,452][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:37:05,952][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:37:06,450][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:37:06,951][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:37:07,453][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:37:07,954][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:37:08,454][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:37:08,955][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:37:09,456][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:37:09,958][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:37:10,458][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:37:10,959][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:37:11,463][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:37:11,966][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:37:12,468][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:37:12,970][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:37:13,471][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:37:13,973][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:37:14,475][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:37:14,977][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:37:15,479][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:37:15,981][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:37:16,482][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:37:16,984][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:37:17,485][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:37:17,986][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:37:18,487][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:37:18,988][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:37:19,489][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21736 tokens. [2026-03-25 18:37:20,102][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:04 [2026-03-25 18:37:20,831][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:37:20,833][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:37:20,835][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:37:21,484][__main__][INFO] - Iteration 130 took 1m 13s (8.33% Gen, 90.79% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 58h 30m 7s. Estimated total time: 61h 32m 15s. Time estimates for 10 more iterations: 12m 18s, 100 more iterations: 2h 3m 4s, 500 more iterations: 10h 15m 22s. [2026-03-25 18:37:21,486][__main__][INFO] - Starting iteration 130. [2026-03-25 18:37:21,887][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:37:21,888][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:37:28,045][__main__][INFO] - Number of regex retries in iteration 130: 0 [2026-03-25 18:37:28,046][__main__][INFO] - agents played in iteration 130 are Bob, Alice [2026-03-25 18:37:28,987][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:37:29,565][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:37:30,025][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:37:30,533][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:37:31,035][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:37:31,538][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:37:32,042][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:37:32,545][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:37:33,048][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:37:33,550][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:37:34,052][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:37:34,553][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:37:35,055][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:37:35,557][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:37:36,059][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:37:36,560][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:37:37,061][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:37:37,564][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:37:38,067][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:37:38,569][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:37:39,072][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:37:39,573][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:37:40,074][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:37:40,575][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:37:41,078][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:37:41,582][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:37:42,086][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:37:42,589][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:37:43,092][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:37:43,595][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:37:44,098][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:37:44,601][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:37:45,105][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:37:45,608][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:37:46,111][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:37:46,613][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:37:47,115][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:37:47,617][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:37:48,120][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:37:48,623][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:37:49,125][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:37:49,627][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:37:50,129][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:37:50,631][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:37:51,133][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:37:51,634][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:37:52,136][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:37:52,638][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:37:53,140][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:37:53,642][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:37:54,143][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:37:54,644][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:37:55,146][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:37:55,647][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:37:56,148][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:37:56,649][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:37:57,150][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:37:57,651][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:37:58,153][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:37:58,655][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:37:59,157][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:37:59,659][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:38:00,161][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:38:00,665][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:38:01,167][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:38:01,669][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:38:02,172][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:38:02,674][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:38:03,177][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:38:03,683][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:38:04,187][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:38:04,690][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:38:05,193][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:38:05,695][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:38:06,198][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:38:06,701][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:38:07,204][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:38:07,707][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:38:08,209][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:38:08,712][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:38:09,213][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:38:09,716][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:38:10,218][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:38:10,720][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:38:11,222][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:38:11,725][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:38:12,228][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:38:12,731][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:38:13,232][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:38:13,735][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:38:14,239][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:38:14,743][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:38:15,246][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:38:15,749][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:38:16,251][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:38:16,753][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:38:17,256][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:38:17,758][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:38:18,260][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:38:18,762][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:38:19,264][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:38:19,766][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:38:20,268][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:38:20,770][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:38:21,271][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:38:21,773][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:38:22,275][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:38:22,777][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:38:23,280][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:38:23,784][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:38:24,286][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:38:24,789][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:38:25,292][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:38:25,795][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:38:26,297][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:38:26,798][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:38:27,299][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:38:27,800][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:38:28,302][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:38:28,805][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:38:29,307][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:38:29,809][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:38:30,312][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:38:30,815][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:38:31,318][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:38:31,822][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:38:32,325][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:38:32,828][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:38:33,331][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:38:33,835][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21748 tokens. [2026-03-25 18:38:34,444][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.66%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:04 [2026-03-25 18:38:35,175][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:38:35,177][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:38:35,179][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:38:36,008][__main__][INFO] - Iteration 131 took 1m 14s (8.31% Gen, 90.57% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 58h 42m 41s. Estimated total time: 61h 46m 4s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 32s, 500 more iterations: 10h 17m 40s. [2026-03-25 18:38:36,010][__main__][INFO] - Starting iteration 131. [2026-03-25 18:38:36,410][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:38:36,411][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:38:39,216][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:38:41,452][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:38:43,086][__main__][INFO] - Number of regex retries in iteration 131: 2 [2026-03-25 18:38:43,087][__main__][INFO] - agents played in iteration 131 are Bob, Alice [2026-03-25 18:38:44,043][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:38:44,624][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:38:45,083][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:38:45,591][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:38:46,093][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:38:46,596][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:38:47,099][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:38:47,602][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:38:48,105][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:38:48,608][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:38:49,113][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:38:49,617][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:38:50,120][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:38:50,623][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:38:51,126][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:38:51,629][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:38:52,133][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:38:52,636][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:38:53,137][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:38:53,638][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:38:54,139][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:38:54,642][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:38:55,143][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:38:55,644][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:38:56,145][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:38:56,647][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:38:57,148][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:38:57,649][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:38:58,149][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:38:58,651][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:38:59,152][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:38:59,653][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:39:00,153][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:39:00,654][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:39:01,156][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:39:01,659][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:39:02,161][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:39:02,663][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:39:03,166][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:39:03,668][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:39:04,171][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:39:04,674][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:39:05,177][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:39:05,679][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:39:06,184][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:39:06,686][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:39:07,189][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:39:07,691][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:39:08,192][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:39:08,694][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:39:09,195][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:39:09,697][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:39:10,199][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:39:10,701][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:39:11,206][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:39:11,709][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:39:12,212][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:39:12,715][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:39:13,216][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:39:13,717][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:39:14,219][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:39:14,722][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:39:15,224][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:39:15,726][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:39:16,227][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:39:16,730][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:39:17,232][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:39:17,734][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:39:18,237][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:39:18,740][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:39:19,242][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:39:19,745][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:39:20,248][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:39:20,751][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:39:21,254][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:39:21,757][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:39:22,260][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:39:22,762][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:39:23,266][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:39:23,769][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:39:24,271][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:39:24,774][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:39:25,275][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:39:25,775][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:39:26,277][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:39:26,778][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:39:27,279][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:39:27,780][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:39:28,282][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:39:28,783][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:39:29,286][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:39:29,787][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:39:30,288][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:39:30,789][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:39:31,290][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:39:31,791][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:39:32,292][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:39:32,792][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:39:33,296][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:39:33,798][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:39:34,300][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:39:34,805][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:39:35,308][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:39:35,811][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:39:36,314][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:39:36,816][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:39:37,319][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:39:37,823][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:39:38,326][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:39:38,829][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:39:39,331][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:39:39,833][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:39:40,333][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:39:40,834][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:39:41,337][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:39:41,839][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:39:42,340][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:39:42,841][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:39:43,342][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:39:43,844][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:39:44,345][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:39:44,846][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:39:45,347][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:39:45,848][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:39:46,348][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:39:46,848][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:39:47,349][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:39:47,850][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:39:48,350][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:39:48,851][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21745 tokens. [2026-03-25 18:39:49,464][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.50%, ΔTime: 00:01:04 [2026-03-25 18:39:50,198][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:39:50,200][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:39:50,202][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:39:50,838][__main__][INFO] - Iteration 132 took 1m 14s (8.97% Gen, 90.17% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 58h 56m 49s. Estimated total time: 62h 1m 26s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 2s, 500 more iterations: 10h 20m 14s. [2026-03-25 18:39:50,840][__main__][INFO] - Starting iteration 132. [2026-03-25 18:39:51,241][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:39:51,241][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:39:57,830][__main__][INFO] - Number of regex retries in iteration 132: 0 [2026-03-25 18:39:57,831][__main__][INFO] - agents played in iteration 132 are Bob, Alice [2026-03-25 18:39:58,790][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:39:59,374][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:39:59,833][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:40:00,339][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:40:00,841][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:40:01,345][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:40:01,847][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:40:02,350][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:40:02,852][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:40:03,353][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:40:03,854][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:40:04,355][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:40:04,856][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:40:05,357][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:40:05,858][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:40:06,360][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:40:06,862][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:40:07,366][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:40:07,866][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:40:08,366][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:40:08,866][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:40:09,366][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:40:09,866][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:40:10,366][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:40:10,866][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:40:11,366][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:40:11,870][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:40:12,373][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:40:12,875][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:40:13,378][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:40:13,881][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:40:14,384][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:40:14,887][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:40:15,390][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:40:15,894][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:40:16,397][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:40:16,901][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:40:17,405][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:40:17,909][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:40:18,412][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:40:18,915][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:40:19,418][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:40:19,920][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:40:20,422][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:40:20,923][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:40:21,424][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:40:21,925][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:40:22,426][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:40:22,928][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:40:23,430][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:40:23,932][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:40:24,433][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:40:24,934][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:40:25,435][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:40:25,936][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:40:26,438][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:40:26,939][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:40:27,439][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:40:27,944][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:40:28,447][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:40:28,950][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:40:29,452][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:40:29,955][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:40:30,457][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:40:30,959][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:40:31,462][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:40:31,964][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:40:32,466][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:40:32,967][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:40:33,470][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:40:33,972][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:40:34,474][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:40:34,975][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:40:35,477][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:40:35,979][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:40:36,484][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:40:36,986][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:40:37,488][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:40:37,990][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:40:38,492][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:40:38,993][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:40:39,494][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:40:39,994][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:40:40,495][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:40:40,994][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:40:41,497][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:40:41,996][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:40:42,496][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:40:42,996][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:40:43,497][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:40:43,999][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:40:44,501][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:40:45,005][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:40:45,508][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:40:46,011][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:40:46,515][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:40:47,018][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:40:47,520][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:40:48,023][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:40:48,526][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:40:49,029][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:40:49,532][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:40:50,035][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:40:50,538][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:40:51,040][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:40:51,544][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:40:52,046][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:40:52,547][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:40:53,048][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:40:53,549][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:40:54,051][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:40:54,552][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:40:55,053][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:40:55,554][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:40:56,057][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:40:56,558][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:40:57,061][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:40:57,563][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:40:58,066][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:40:58,567][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:40:59,070][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:40:59,571][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:41:00,073][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:41:00,574][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:41:01,076][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:41:01,577][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:41:02,078][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:41:02,580][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:41:03,085][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:41:03,587][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 18:41:04,206][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 18:41:04,940][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:41:04,943][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:41:04,944][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:41:05,615][__main__][INFO] - Iteration 133 took 1m 14s (8.86% Gen, 90.24% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 58h 52m 51s. Estimated total time: 61h 58m 43s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 57s, 500 more iterations: 10h 19m 47s. [2026-03-25 18:41:05,617][__main__][INFO] - Starting iteration 133. [2026-03-25 18:41:06,022][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:41:06,023][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:41:12,508][__main__][INFO] - Number of regex retries in iteration 133: 0 [2026-03-25 18:41:12,509][__main__][INFO] - agents played in iteration 133 are Bob, Alice [2026-03-25 18:41:13,454][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:41:14,034][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:41:14,494][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:41:15,001][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:41:15,503][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:41:16,006][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:41:16,508][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:41:17,010][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:41:17,512][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:41:18,014][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:41:18,516][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:41:19,016][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:41:19,517][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:41:20,016][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:41:20,517][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:41:21,018][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:41:21,518][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:41:22,019][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:41:22,521][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:41:23,022][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:41:23,524][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:41:24,025][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:41:24,527][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:41:25,028][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:41:25,530][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:41:26,032][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:41:26,532][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:41:27,032][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:41:27,533][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:41:28,033][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:41:28,534][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:41:29,034][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:41:29,534][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:41:30,034][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:41:30,537][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:41:31,039][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:41:31,541][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:41:32,043][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:41:32,544][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:41:33,046][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:41:33,548][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:41:34,050][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:41:34,550][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:41:35,051][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:41:35,548][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:41:36,049][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:41:36,550][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:41:37,052][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:41:37,552][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:41:38,054][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:41:38,554][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:41:39,054][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:41:39,555][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:41:40,055][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:41:40,555][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:41:41,056][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:41:41,558][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:41:42,058][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:41:42,559][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:41:43,061][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:41:43,562][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:41:44,063][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:41:44,563][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:41:45,064][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:41:45,565][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:41:46,067][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:41:46,567][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:41:47,069][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:41:47,569][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:41:48,071][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:41:48,571][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:41:49,072][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:41:49,572][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:41:50,074][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:41:50,574][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:41:51,073][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:41:51,573][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:41:52,072][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:41:52,572][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:41:53,071][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:41:53,572][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:41:54,073][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:41:54,574][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:41:55,075][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:41:55,575][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:41:56,077][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:41:56,578][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:41:57,080][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:41:57,580][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:41:58,082][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:41:58,583][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:41:59,085][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:41:59,586][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:42:00,086][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:42:00,586][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:42:01,086][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:42:01,587][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:42:02,086][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:42:02,587][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:42:03,089][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:42:03,590][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:42:04,092][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:42:04,593][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:42:05,095][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:42:05,596][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:42:06,098][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:42:06,599][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:42:07,100][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:42:07,600][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:42:08,103][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:42:08,604][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:42:09,106][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:42:09,608][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:42:10,109][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:42:10,610][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:42:11,113][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:42:11,616][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:42:12,117][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:42:12,618][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:42:13,118][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:42:13,619][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:42:14,120][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:42:14,623][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:42:15,124][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:42:15,625][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:42:16,127][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:42:16,627][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:42:17,128][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:42:17,629][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:42:18,129][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21719 tokens. [2026-03-25 18:42:18,743][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 18:42:19,473][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:42:19,475][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:42:19,477][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:42:20,326][__main__][INFO] - Iteration 134 took 1m 14s (8.73% Gen, 90.13% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 48m 5s. Estimated total time: 61h 55m 12s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 50s, 500 more iterations: 10h 19m 12s. [2026-03-25 18:42:20,327][__main__][INFO] - Starting iteration 134. [2026-03-25 18:42:20,730][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:42:20,731][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:42:27,274][__main__][INFO] - Number of regex retries in iteration 134: 0 [2026-03-25 18:42:27,275][__main__][INFO] - agents played in iteration 134 are Bob, Alice [2026-03-25 18:42:28,214][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:42:28,786][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:42:29,243][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:42:29,749][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:42:30,249][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:42:30,749][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:42:31,249][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:42:31,749][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:42:32,249][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:42:32,749][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:42:33,249][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:42:33,749][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:42:34,249][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:42:34,749][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:42:35,249][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:42:35,749][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:42:36,249][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:42:36,749][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:42:37,250][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:42:37,749][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:42:38,250][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:42:38,749][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:42:39,249][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:42:39,749][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:42:40,249][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:42:40,750][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:42:41,251][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:42:41,749][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:42:42,249][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:42:42,747][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:42:43,247][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:42:43,747][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:42:44,248][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:42:44,749][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:42:45,251][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:42:45,753][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:42:46,254][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:42:46,755][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:42:47,256][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:42:47,758][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:42:48,259][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:42:48,760][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:42:49,260][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:42:49,761][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:42:50,262][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:42:50,762][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:42:51,263][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:42:51,763][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:42:52,263][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:42:52,763][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:42:53,265][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:42:53,765][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:42:54,265][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:42:54,764][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:42:55,265][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:42:55,764][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:42:56,263][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:42:56,765][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:42:57,266][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:42:57,766][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:42:58,267][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:42:58,768][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:42:59,269][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:42:59,770][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:43:00,271][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:43:00,771][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:43:01,270][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:43:01,770][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:43:02,269][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:43:02,768][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:43:03,264][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:43:03,764][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:43:04,263][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:43:04,763][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:43:05,263][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:43:05,763][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:43:06,262][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:43:06,763][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:43:07,266][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:43:07,767][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:43:08,266][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:43:08,766][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:43:09,267][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:43:09,766][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:43:10,266][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:43:10,766][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:43:11,268][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:43:11,768][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:43:12,268][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:43:12,768][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:43:13,268][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:43:13,768][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:43:14,269][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:43:14,769][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:43:15,269][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:43:15,769][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:43:16,268][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:43:16,768][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:43:17,269][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:43:17,770][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:43:18,272][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:43:18,773][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:43:19,275][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:43:19,776][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:43:20,276][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:43:20,777][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:43:21,277][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:43:21,777][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:43:22,277][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:43:22,777][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:43:23,277][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:43:23,776][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:43:24,275][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:43:24,775][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:43:25,275][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:43:25,775][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:43:26,275][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:43:26,770][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:43:27,269][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:43:27,769][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:43:28,269][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:43:28,769][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:43:29,270][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:43:29,770][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:43:30,270][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:43:30,770][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:43:31,270][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:43:31,771][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:43:32,272][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:43:32,772][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21620 tokens. [2026-03-25 18:43:33,375][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.28%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 18:43:34,102][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:43:34,104][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:43:34,106][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:43:34,772][__main__][INFO] - Iteration 135 took 1m 14s (8.84% Gen, 90.26% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 33m 46s. Estimated total time: 61h 42m 7s. Time estimates for 10 more iterations: 12m 20s, 100 more iterations: 2h 3m 24s, 500 more iterations: 10h 17m 1s. [2026-03-25 18:43:34,774][__main__][INFO] - Starting iteration 135. [2026-03-25 18:43:35,179][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:43:35,180][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:43:39,854][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:43:41,920][__main__][INFO] - Number of regex retries in iteration 135: 1 [2026-03-25 18:43:41,921][__main__][INFO] - agents played in iteration 135 are Bob, Alice [2026-03-25 18:43:42,876][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:43:43,449][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:43:43,906][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:43:44,411][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:43:44,911][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:43:45,412][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:43:45,913][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:43:46,414][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:43:46,914][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:43:47,414][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:43:47,916][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:43:48,417][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:43:48,919][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:43:49,420][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:43:49,921][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:43:50,422][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:43:50,923][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:43:51,425][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:43:51,925][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:43:52,425][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:43:52,926][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:43:53,426][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:43:53,926][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:43:54,426][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:43:54,926][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:43:55,426][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:43:55,926][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:43:56,426][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:43:56,927][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:43:57,427][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:43:57,927][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:43:58,427][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:43:58,927][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:43:59,427][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:43:59,927][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:44:00,427][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:44:00,927][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:44:01,427][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:44:01,927][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:44:02,427][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:44:02,927][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:44:03,428][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:44:03,929][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:44:04,430][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:44:04,930][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:44:05,431][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:44:05,932][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:44:06,433][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:44:06,934][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:44:07,435][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:44:07,935][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:44:08,435][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:44:08,935][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:44:09,435][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:44:09,937][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:44:10,437][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:44:10,937][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:44:11,439][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:44:11,941][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:44:12,443][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:44:12,944][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:44:13,445][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:44:13,946][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:44:14,447][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:44:14,947][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:44:15,447][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:44:15,946][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:44:16,446][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:44:16,945][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:44:17,444][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:44:17,944][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:44:18,444][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:44:18,944][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:44:19,444][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:44:19,945][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:44:20,446][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:44:20,946][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:44:21,447][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:44:21,948][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:44:22,449][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:44:22,949][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:44:23,450][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:44:23,950][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:44:24,450][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:44:24,949][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:44:25,450][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:44:25,949][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:44:26,449][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:44:26,949][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:44:27,449][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:44:27,949][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:44:28,449][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:44:28,949][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:44:29,450][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:44:29,951][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:44:30,452][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:44:30,953][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:44:31,453][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:44:31,952][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:44:32,451][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:44:32,951][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:44:33,452][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:44:33,952][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:44:34,451][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:44:34,951][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:44:35,451][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:44:35,951][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:44:36,452][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:44:36,954][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:44:37,456][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:44:37,958][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:44:38,460][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:44:38,962][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:44:39,463][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:44:39,965][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:44:40,465][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:44:40,965][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:44:41,469][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:44:41,969][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:44:42,470][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:44:42,970][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:44:43,471][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:44:43,970][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:44:44,471][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:44:44,970][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:44:45,471][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:44:45,971][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:44:46,468][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:44:46,969][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:44:47,469][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21738 tokens. [2026-03-25 18:44:48,075][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-25 18:44:48,805][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:44:48,807][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:44:48,808][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:44:49,693][__main__][INFO] - Iteration 136 took 1m 14s (9.05% Gen, 89.76% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 56m 8s. Estimated total time: 62h 5m 44s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 11s, 500 more iterations: 10h 20m 57s. [2026-03-25 18:44:49,698][__main__][INFO] - Starting iteration 136. [2026-03-25 18:44:50,099][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:44:50,100][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:44:56,448][__main__][INFO] - Number of regex retries in iteration 136: 0 [2026-03-25 18:44:56,449][__main__][INFO] - agents played in iteration 136 are Bob, Alice [2026-03-25 18:44:57,649][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:44:58,222][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:44:58,678][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:44:59,183][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:44:59,685][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:45:00,185][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:45:00,686][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:45:01,185][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:45:01,685][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:45:02,185][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:45:02,686][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:45:03,187][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:45:03,687][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:45:04,187][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:45:04,686][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:45:05,186][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:45:05,686][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:45:06,186][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:45:06,688][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:45:07,189][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:45:07,690][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:45:08,190][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:45:08,690][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:45:09,190][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:45:09,691][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:45:10,191][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:45:10,710][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:45:11,216][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:45:11,717][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:45:12,219][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:45:12,721][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:45:13,221][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:45:13,722][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:45:14,225][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:45:14,727][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:45:15,230][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:45:15,734][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:45:16,238][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:45:16,738][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:45:17,238][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:45:17,738][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:45:18,239][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:45:18,740][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:45:19,241][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:45:19,741][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:45:20,240][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:45:20,740][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:45:21,241][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:45:21,742][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:45:22,243][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:45:22,745][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:45:23,247][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:45:23,748][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:45:24,250][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:45:24,751][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:45:25,253][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:45:25,754][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:45:26,255][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:45:26,756][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:45:27,257][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:45:27,758][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:45:28,259][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:45:28,760][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:45:29,261][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:45:29,762][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:45:30,263][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:45:30,764][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:45:31,264][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:45:31,763][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:45:32,262][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:45:32,761][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:45:33,260][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:45:33,758][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:45:34,257][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:45:34,757][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:45:35,256][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:45:35,755][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:45:36,254][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:45:36,754][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:45:37,253][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:45:37,752][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:45:38,252][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:45:38,752][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:45:39,252][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:45:39,752][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:45:40,253][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:45:40,753][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:45:41,255][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:45:41,756][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:45:42,256][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:45:42,757][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:45:43,258][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:45:43,759][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:45:44,259][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:45:44,762][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:45:45,262][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:45:45,764][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:45:46,265][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:45:46,766][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:45:47,267][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:45:47,767][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:45:48,268][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:45:48,769][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:45:49,270][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:45:49,771][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:45:50,271][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:45:50,771][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:45:51,271][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:45:51,772][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:45:52,272][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:45:52,772][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:45:53,272][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:45:53,772][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:45:54,271][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:45:54,772][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:45:55,273][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:45:55,775][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:45:56,276][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:45:56,777][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:45:57,278][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:45:57,780][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:45:58,283][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:45:58,784][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:45:59,285][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:45:59,787][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:46:00,288][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:46:00,790][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:46:01,290][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:46:01,791][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:46:02,292][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21733 tokens. [2026-03-25 18:46:02,898][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.38%, ΔTime: 00:01:04 [2026-03-25 18:46:03,624][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:46:03,626][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:46:03,628][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:46:04,456][__main__][INFO] - Iteration 137 took 1m 14s (8.54% Gen, 90.35% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 58h 47m 1s. Estimated total time: 61h 57m 52s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 55s, 500 more iterations: 10h 19m 38s. [2026-03-25 18:46:04,458][__main__][INFO] - Starting iteration 137. [2026-03-25 18:46:04,861][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:46:04,861][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:46:09,668][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:46:11,141][__main__][INFO] - Number of regex retries in iteration 137: 1 [2026-03-25 18:46:11,142][__main__][INFO] - agents played in iteration 137 are Bob, Alice [2026-03-25 18:46:12,097][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:46:12,671][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:46:13,129][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:46:13,636][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:46:14,137][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:46:14,638][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:46:15,139][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:46:15,643][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:46:16,145][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:46:16,646][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:46:17,146][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:46:17,646][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:46:18,146][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:46:18,647][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:46:19,147][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:46:19,647][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:46:20,147][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:46:20,646][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:46:21,147][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:46:21,647][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:46:22,148][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:46:22,649][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:46:23,150][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:46:23,651][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:46:24,151][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:46:24,651][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:46:25,152][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:46:25,652][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:46:26,153][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:46:26,653][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:46:27,154][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:46:27,654][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:46:28,154][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:46:28,654][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:46:29,152][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:46:29,652][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:46:30,151][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:46:30,651][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:46:31,149][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:46:31,649][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:46:32,148][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:46:32,647][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:46:33,147][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:46:33,648][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:46:34,148][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:46:34,648][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:46:35,149][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:46:35,650][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:46:36,150][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:46:36,651][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:46:37,151][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:46:37,652][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:46:38,152][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:46:38,652][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:46:39,153][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:46:39,652][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:46:40,153][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:46:40,653][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:46:41,153][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:46:41,655][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:46:42,155][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:46:42,655][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:46:43,155][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:46:43,655][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:46:44,155][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:46:44,655][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:46:45,156][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:46:45,657][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:46:46,159][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:46:46,661][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:46:47,164][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:46:47,665][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:46:48,167][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:46:48,668][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:46:49,168][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:46:49,667][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:46:50,167][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:46:50,666][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:46:51,166][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:46:51,666][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:46:52,166][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:46:52,666][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:46:53,166][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:46:53,667][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:46:54,167][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:46:54,667][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:46:55,168][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:46:55,668][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:46:56,169][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:46:56,669][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:46:57,170][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:46:57,670][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:46:58,171][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:46:58,671][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:46:59,172][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:46:59,672][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:47:00,173][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:47:00,673][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:47:01,172][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:47:01,671][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:47:02,169][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:47:02,669][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:47:03,168][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:47:03,667][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:47:04,166][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:47:04,665][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:47:05,166][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:47:05,666][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:47:06,166][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:47:06,667][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:47:07,167][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:47:07,668][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:47:08,169][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:47:08,669][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:47:09,169][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:47:09,669][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:47:10,170][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:47:10,670][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:47:11,170][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:47:11,672][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:47:12,172][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:47:12,672][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:47:13,172][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:47:13,673][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:47:14,173][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:47:14,673][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:47:15,173][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:47:15,673][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:47:16,172][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:47:16,672][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 18:47:17,275][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 18:47:17,999][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:47:18,001][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:47:18,002][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:47:18,828][__main__][INFO] - Iteration 138 took 1m 13s (8.49% Gen, 90.39% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 26m 17s. Estimated total time: 61h 38m 22s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 16s, 500 more iterations: 10h 16m 23s. [2026-03-25 18:47:18,830][__main__][INFO] - Starting iteration 138. [2026-03-25 18:47:19,233][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:47:19,233][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:47:23,537][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:47:25,718][__main__][INFO] - Number of regex retries in iteration 138: 1 [2026-03-25 18:47:25,719][__main__][INFO] - agents played in iteration 138 are Bob, Alice [2026-03-25 18:47:26,652][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:47:27,231][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:47:27,688][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:47:28,193][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:47:28,694][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:47:29,194][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:47:29,695][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:47:30,196][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:47:30,697][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:47:31,197][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:47:31,698][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:47:32,199][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:47:32,699][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:47:33,202][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:47:33,703][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:47:34,204][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:47:34,705][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:47:35,207][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:47:35,707][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:47:36,208][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:47:36,708][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:47:37,210][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:47:37,710][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:47:38,211][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:47:38,711][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:47:39,211][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:47:39,712][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:47:40,214][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:47:40,714][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:47:41,214][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:47:41,715][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:47:42,215][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:47:42,716][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:47:43,216][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:47:43,717][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:47:44,218][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:47:44,718][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:47:45,218][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:47:45,719][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:47:46,219][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:47:46,720][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:47:47,221][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:47:47,721][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:47:48,221][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:47:48,722][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:47:49,223][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:47:49,724][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:47:50,225][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:47:50,725][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:47:51,226][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:47:51,729][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:47:52,231][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:47:52,732][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:47:53,233][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:47:53,734][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:47:54,235][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:47:54,737][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:47:55,238][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:47:55,738][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:47:56,238][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:47:56,738][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:47:57,238][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:47:57,738][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:47:58,237][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:47:58,737][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:47:59,237][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:47:59,738][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:48:00,239][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:48:00,739][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:48:01,240][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:48:01,740][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:48:02,242][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:48:02,744][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:48:03,244][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:48:03,745][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:48:04,245][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:48:04,746][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:48:05,247][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:48:05,748][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:48:06,248][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:48:06,749][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:48:07,250][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:48:07,749][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:48:08,249][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:48:08,750][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:48:09,250][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:48:09,751][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:48:10,250][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:48:10,749][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:48:11,251][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:48:11,752][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:48:12,253][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:48:12,753][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:48:13,254][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:48:13,754][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:48:14,256][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:48:14,755][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:48:15,256][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:48:15,755][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:48:16,255][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:48:16,756][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:48:17,255][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:48:17,755][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:48:18,255][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:48:18,756][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:48:19,257][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:48:19,758][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:48:20,259][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:48:20,759][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:48:21,258][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:48:21,758][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:48:22,258][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:48:22,758][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:48:23,258][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:48:23,759][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:48:24,260][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:48:24,761][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:48:25,261][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:48:25,764][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:48:26,266][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:48:26,767][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:48:27,268][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:48:27,769][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:48:28,269][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:48:28,770][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:48:29,271][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:48:29,773][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:48:30,273][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:48:30,774][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:48:31,274][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 18:48:31,885][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 18:48:32,612][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:48:32,614][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:48:32,616][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:48:33,233][__main__][INFO] - Iteration 139 took 1m 14s (8.76% Gen, 90.40% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 26m 41s. Estimated total time: 61h 40m 1s. Time estimates for 10 more iterations: 12m 20s, 100 more iterations: 2h 3m 20s, 500 more iterations: 10h 16m 40s. [2026-03-25 18:48:33,235][__main__][INFO] - Starting iteration 139. [2026-03-25 18:48:33,637][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:48:33,638][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:48:39,997][__main__][INFO] - Number of regex retries in iteration 139: 0 [2026-03-25 18:48:39,998][__main__][INFO] - agents played in iteration 139 are Bob, Alice [2026-03-25 18:48:40,936][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:48:41,514][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:48:41,971][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:48:42,475][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:48:42,974][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:48:43,474][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:48:43,974][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:48:44,475][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:48:44,974][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:48:45,474][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:48:45,976][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:48:46,475][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:48:46,975][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:48:47,475][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:48:47,975][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:48:48,475][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:48:48,976][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:48:49,476][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:48:49,977][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:48:50,478][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:48:50,979][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:48:51,480][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:48:51,981][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:48:52,482][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:48:52,983][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:48:53,486][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:48:54,005][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:48:54,510][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:48:55,011][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:48:55,512][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:48:56,013][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:48:56,514][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:48:57,015][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:48:57,515][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:48:58,015][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:48:58,516][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:48:59,016][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:48:59,516][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:49:00,017][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:49:00,517][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:49:01,017][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:49:01,517][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:49:02,018][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:49:02,518][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:49:03,019][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:49:03,520][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:49:04,021][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:49:04,521][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:49:05,021][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:49:05,523][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:49:06,025][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:49:06,527][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:49:07,029][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:49:07,532][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:49:08,032][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:49:08,534][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:49:09,034][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:49:09,535][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:49:10,035][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:49:10,536][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:49:11,036][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:49:11,539][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:49:12,039][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:49:12,540][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:49:13,040][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:49:13,541][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:49:14,042][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:49:14,543][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:49:15,043][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:49:15,546][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:49:16,046][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:49:16,546][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:49:17,046][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:49:17,546][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:49:18,046][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:49:18,546][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:49:19,047][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:49:19,549][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:49:20,052][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:49:20,552][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:49:21,052][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:49:21,552][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:49:22,053][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:49:22,553][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:49:23,053][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:49:23,555][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:49:24,055][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:49:24,556][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:49:25,056][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:49:25,557][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:49:26,060][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:49:26,560][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:49:27,062][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:49:27,565][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:49:28,067][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:49:28,568][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:49:29,070][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:49:29,572][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:49:30,072][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:49:30,572][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:49:31,072][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:49:31,573][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:49:32,073][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:49:32,573][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:49:33,073][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:49:33,573][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:49:34,073][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:49:34,573][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:49:35,073][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:49:35,574][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:49:36,074][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:49:36,574][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:49:37,074][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:49:37,574][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:49:38,075][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:49:38,575][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:49:39,076][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:49:39,577][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:49:40,077][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:49:40,577][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:49:41,079][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:49:41,582][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:49:42,084][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:49:42,585][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:49:43,085][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:49:43,587][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:49:44,087][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:49:44,588][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:49:45,088][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:49:45,589][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21749 tokens. [2026-03-25 18:49:46,200][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 18:49:46,931][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:49:46,933][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:49:46,935][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:49:47,737][__main__][INFO] - Iteration 140 took 1m 14s (8.58% Gen, 90.33% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 30m 26s. Estimated total time: 61h 45m 1s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 30s, 500 more iterations: 10h 17m 30s. [2026-03-25 18:49:47,739][__main__][INFO] - Starting iteration 140. [2026-03-25 18:49:48,140][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:49:48,140][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:49:48,740][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:49:54,279][__main__][INFO] - Number of regex retries in iteration 140: 1 [2026-03-25 18:49:54,280][__main__][INFO] - agents played in iteration 140 are Bob, Alice [2026-03-25 18:49:55,199][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:49:55,780][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:49:56,235][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:49:56,739][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:49:57,238][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:49:57,737][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:49:58,237][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:49:58,737][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:49:59,237][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:49:59,737][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:50:00,241][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:50:00,745][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:50:01,248][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:50:01,752][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:50:02,256][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:50:02,759][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:50:03,261][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:50:03,766][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:50:04,267][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:50:04,767][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:50:05,268][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:50:05,768][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:50:06,268][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:50:06,769][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:50:07,269][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:50:07,770][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:50:08,271][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:50:08,770][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:50:09,271][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:50:09,770][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:50:10,270][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:50:10,770][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:50:11,272][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:50:11,773][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:50:12,275][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:50:12,776][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:50:13,279][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:50:13,782][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:50:14,285][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:50:14,787][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:50:15,289][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:50:15,791][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:50:16,291][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:50:16,792][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:50:17,293][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:50:17,793][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:50:18,293][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:50:18,793][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:50:19,293][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:50:19,793][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:50:20,296][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:50:20,799][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:50:21,301][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:50:21,802][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:50:22,305][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:50:22,806][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:50:23,308][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:50:23,810][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:50:24,311][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:50:24,812][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:50:25,313][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:50:25,813][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:50:26,313][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:50:26,814][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:50:27,315][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:50:27,815][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:50:28,314][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:50:28,814][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:50:29,313][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:50:29,813][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:50:30,314][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:50:30,813][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:50:31,313][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:50:31,813][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:50:32,316][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:50:32,819][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:50:33,324][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:50:33,827][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:50:34,331][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:50:34,835][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:50:35,338][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:50:35,843][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:50:36,344][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:50:36,845][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:50:37,348][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:50:37,849][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:50:38,350][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:50:38,851][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:50:39,351][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:50:39,852][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:50:40,351][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:50:40,851][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:50:41,353][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:50:41,854][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:50:42,352][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:50:42,852][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:50:43,352][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:50:43,852][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:50:44,354][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:50:44,854][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:50:45,355][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:50:45,856][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:50:46,357][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:50:46,858][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:50:47,358][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:50:47,861][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:50:48,362][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:50:48,865][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:50:49,365][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:50:49,866][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:50:50,366][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:50:50,866][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:50:51,367][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:50:51,867][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:50:52,368][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:50:52,869][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:50:53,370][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:50:53,870][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:50:54,371][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:50:54,873][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:50:55,374][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:50:55,875][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:50:56,376][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:50:56,876][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:50:57,374][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:50:57,875][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:50:58,375][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:50:58,876][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:50:59,376][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:50:59,876][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21730 tokens. [2026-03-25 18:51:00,507][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:04 [2026-03-25 18:51:01,241][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:51:01,243][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:51:01,245][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:51:02,099][__main__][INFO] - Iteration 141 took 1m 13s (8.30% Gen, 90.54% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 22m 10s. Estimated total time: 61h 37m 59s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 15s, 500 more iterations: 10h 16m 19s. [2026-03-25 18:51:02,102][__main__][INFO] - Starting iteration 141. [2026-03-25 18:51:02,503][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:51:02,504][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:51:08,608][__main__][INFO] - Number of regex retries in iteration 141: 0 [2026-03-25 18:51:08,609][__main__][INFO] - agents played in iteration 141 are Bob, Alice [2026-03-25 18:51:09,537][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:51:10,118][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:51:10,572][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:51:11,073][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:51:11,572][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:51:12,068][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:51:12,565][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:51:13,064][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:51:13,562][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:51:14,059][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:51:14,560][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:51:15,061][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:51:15,561][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:51:16,061][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:51:16,561][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:51:17,063][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:51:17,564][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:51:18,064][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:51:18,567][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:51:19,069][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:51:19,570][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:51:20,070][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:51:20,573][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:51:21,074][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:51:21,629][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:51:22,132][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:51:22,632][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:51:23,132][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:51:23,632][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:51:24,132][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:51:24,632][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:51:25,132][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:51:25,631][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:51:26,131][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:51:26,631][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:51:27,132][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:51:27,632][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:51:28,133][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:51:28,633][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:51:29,133][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:51:29,632][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:51:30,132][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:51:30,632][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:51:31,132][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:51:31,633][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:51:32,133][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:51:32,633][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:51:33,132][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:51:33,632][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:51:34,133][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:51:34,652][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:51:35,156][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:51:35,657][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:51:36,160][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:51:36,661][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:51:37,163][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:51:37,665][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:51:38,166][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:51:38,667][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:51:39,167][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:51:39,667][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:51:40,167][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:51:40,667][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:51:41,168][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:51:41,669][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:51:42,169][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:51:42,666][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:51:43,163][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:51:43,661][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:51:44,158][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:51:44,655][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:51:45,151][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:51:45,648][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:51:46,145][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:51:46,646][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:51:47,146][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:51:47,646][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:51:48,147][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:51:48,648][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:51:49,148][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:51:49,648][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:51:50,148][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:51:50,649][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:51:51,150][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:51:51,652][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:51:52,152][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:51:52,653][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:51:53,154][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:51:53,654][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:51:54,155][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:51:54,654][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:51:55,154][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:51:55,653][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:51:56,152][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:51:56,652][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:51:57,151][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:51:57,650][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:51:58,150][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:51:58,651][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:51:59,150][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:51:59,650][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:52:00,150][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:52:00,650][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:52:01,150][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:52:01,650][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:52:02,150][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:52:02,650][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:52:03,149][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:52:03,649][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:52:04,149][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:52:04,650][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:52:05,150][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:52:05,650][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:52:06,150][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:52:06,651][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:52:07,153][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:52:07,655][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:52:08,156][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:52:08,657][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:52:09,159][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:52:09,659][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:52:10,161][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:52:10,660][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:52:11,160][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:52:11,663][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:52:12,164][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:52:12,664][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:52:13,164][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:52:13,663][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:52:14,164][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 18:52:14,774][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.27%, ΔTime: 00:01:04 [2026-03-25 18:52:15,504][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:52:15,506][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:52:15,508][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:52:16,132][__main__][INFO] - Iteration 142 took 1m 13s (8.29% Gen, 90.86% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 4m 24s. Estimated total time: 61h 21m 27s. Time estimates for 10 more iterations: 12m 16s, 100 more iterations: 2h 2m 42s, 500 more iterations: 10h 13m 34s. [2026-03-25 18:52:16,134][__main__][INFO] - Starting iteration 142. [2026-03-25 18:52:16,534][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:52:16,535][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:52:19,697][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:52:22,984][__main__][INFO] - Number of regex retries in iteration 142: 1 [2026-03-25 18:52:22,985][__main__][INFO] - agents played in iteration 142 are Bob, Alice [2026-03-25 18:52:23,901][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:52:24,476][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:52:24,932][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:52:25,438][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:52:25,939][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:52:26,439][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:52:26,941][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:52:27,442][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:52:27,942][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:52:28,443][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:52:28,945][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:52:29,446][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:52:29,947][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:52:30,448][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:52:30,950][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:52:31,450][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:52:31,951][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:52:32,452][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:52:32,952][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:52:33,452][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:52:33,951][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:52:34,450][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:52:34,950][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:52:35,461][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:52:35,961][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:52:36,460][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:52:36,960][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:52:37,459][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:52:37,958][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:52:38,459][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:52:38,959][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:52:39,459][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:52:39,958][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:52:40,458][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:52:40,956][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:52:41,458][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:52:41,958][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:52:42,457][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:52:42,957][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:52:43,456][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:52:43,955][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:52:44,456][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:52:44,956][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:52:45,456][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:52:45,957][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:52:46,458][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:52:46,958][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:52:47,458][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:52:47,957][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:52:48,458][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:52:48,959][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:52:49,459][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:52:49,959][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:52:50,459][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:52:50,959][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:52:51,460][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:52:51,959][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:52:52,460][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:52:52,958][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:52:53,457][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:52:53,957][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:52:54,455][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:52:54,954][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:52:55,452][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:52:55,951][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:52:56,450][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:52:56,950][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:52:57,452][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:52:57,953][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:52:58,453][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:52:58,953][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:52:59,454][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:52:59,954][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:53:00,454][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:53:00,956][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:53:01,456][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:53:01,958][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:53:02,459][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:53:02,959][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:53:03,460][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:53:03,962][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:53:04,464][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:53:04,963][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:53:05,462][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:53:05,960][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:53:06,461][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:53:06,962][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:53:07,462][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:53:07,962][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:53:08,461][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:53:08,961][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:53:09,460][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:53:09,961][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:53:10,461][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:53:10,962][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:53:11,465][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:53:11,966][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:53:12,465][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:53:12,964][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:53:13,465][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:53:13,965][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:53:14,464][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:53:14,964][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:53:15,463][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:53:15,962][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:53:16,461][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:53:16,963][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:53:17,463][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:53:17,964][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:53:18,465][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:53:18,965][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:53:19,465][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:53:19,965][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:53:20,466][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:53:20,966][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:53:21,467][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:53:21,967][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:53:22,468][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:53:22,968][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:53:23,470][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:53:23,971][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:53:24,472][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:53:24,971][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:53:25,471][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:53:25,970][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:53:26,469][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:53:26,968][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:53:27,467][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:53:27,966][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:53:28,466][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21714 tokens. [2026-03-25 18:53:29,071][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-25 18:53:29,865][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:53:29,868][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:53:29,869][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:53:30,575][__main__][INFO] - Iteration 143 took 1m 14s (8.71% Gen, 90.33% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 23m 47s. Estimated total time: 61h 42m 4s. Time estimates for 10 more iterations: 12m 20s, 100 more iterations: 2h 3m 24s, 500 more iterations: 10h 17m 0s. [2026-03-25 18:53:30,577][__main__][INFO] - Starting iteration 143. [2026-03-25 18:53:30,980][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:53:30,981][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:53:37,774][__main__][INFO] - Number of regex retries in iteration 143: 0 [2026-03-25 18:53:37,775][__main__][INFO] - agents played in iteration 143 are Bob, Alice [2026-03-25 18:53:38,692][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:53:39,268][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:53:39,726][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:53:40,234][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:53:40,737][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:53:41,240][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:53:41,745][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:53:42,248][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:53:42,749][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:53:43,252][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:53:43,752][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:53:44,253][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:53:44,753][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:53:45,252][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:53:45,753][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:53:46,253][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:53:46,753][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:53:47,253][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:53:47,752][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:53:48,252][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:53:48,752][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:53:49,252][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:53:49,752][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:53:50,252][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:53:50,751][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:53:51,250][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:53:51,751][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:53:52,252][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:53:52,753][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:53:53,254][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:53:53,755][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:53:54,256][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:53:54,756][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:53:55,257][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:53:55,758][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:53:56,259][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:53:56,760][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:53:57,261][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:53:57,761][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:53:58,264][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:53:58,765][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:53:59,266][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:53:59,767][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:54:00,267][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:54:00,767][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:54:01,267][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:54:01,769][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:54:02,269][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:54:02,770][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:54:03,271][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:54:03,771][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:54:04,271][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:54:04,772][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:54:05,272][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:54:05,773][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:54:06,273][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:54:06,774][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:54:07,274][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:54:07,773][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:54:08,273][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:54:08,772][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:54:09,272][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:54:09,772][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:54:10,271][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:54:10,771][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:54:11,272][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:54:11,775][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:54:12,276][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:54:12,778][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:54:13,278][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:54:13,779][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:54:14,281][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:54:14,785][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:54:15,286][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:54:15,786][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:54:16,287][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:54:16,787][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:54:17,288][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:54:17,789][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:54:18,289][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:54:18,790][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:54:19,290][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:54:19,789][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:54:20,289][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:54:20,788][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:54:21,288][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:54:21,787][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:54:22,287][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:54:22,787][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:54:23,286][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:54:23,787][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:54:24,288][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:54:24,790][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:54:25,294][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:54:25,796][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:54:26,295][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:54:26,797][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:54:27,298][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:54:27,799][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:54:28,300][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:54:28,801][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:54:29,303][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:54:29,805][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:54:30,307][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:54:30,808][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:54:31,310][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:54:31,811][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:54:32,312][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:54:32,813][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:54:33,313][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:54:33,814][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:54:34,316][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:54:34,816][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:54:35,316][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:54:35,817][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:54:36,316][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:54:36,816][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:54:37,315][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:54:37,815][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:54:38,316][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:54:38,816][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:54:39,316][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:54:39,816][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:54:40,315][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:54:40,815][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:54:41,317][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:54:41,819][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:54:42,318][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:54:42,818][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:54:43,318][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21733 tokens. [2026-03-25 18:54:43,926][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 18:54:44,653][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:54:44,656][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:54:44,657][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:54:45,289][__main__][INFO] - Iteration 144 took 1m 14s (9.14% Gen, 90.01% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 35m 54s. Estimated total time: 61h 55m 26s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 50s, 500 more iterations: 10h 19m 14s. [2026-03-25 18:54:45,291][__main__][INFO] - Starting iteration 144. [2026-03-25 18:54:45,690][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:54:45,691][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:54:51,929][__main__][INFO] - Number of regex retries in iteration 144: 0 [2026-03-25 18:54:51,929][__main__][INFO] - agents played in iteration 144 are Bob, Alice [2026-03-25 18:54:52,842][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:54:53,419][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:54:53,874][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:54:54,378][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:54:54,878][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:54:55,378][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:54:55,878][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:54:56,378][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:54:56,878][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:54:57,377][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:54:57,878][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:54:58,378][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:54:58,878][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:54:59,379][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:54:59,879][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:55:00,380][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:55:00,879][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:55:01,379][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:55:01,878][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:55:02,376][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:55:02,875][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:55:03,374][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:55:03,874][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:55:04,373][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:55:04,872][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:55:05,371][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:55:05,872][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:55:06,373][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:55:06,873][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:55:07,376][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:55:07,876][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:55:08,377][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:55:08,876][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:55:09,376][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:55:09,875][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:55:10,375][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:55:10,876][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:55:11,377][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:55:11,877][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:55:12,377][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:55:12,879][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:55:13,379][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:55:13,880][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:55:14,381][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:55:14,880][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:55:15,376][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:55:15,876][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:55:16,376][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:55:16,875][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:55:17,375][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:55:17,875][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:55:18,374][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:55:18,874][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:55:19,373][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:55:19,871][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:55:20,371][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:55:20,870][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:55:21,370][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:55:21,869][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:55:22,369][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:55:22,868][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:55:23,367][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:55:23,866][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:55:24,365][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:55:24,865][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:55:25,364][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:55:25,863][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:55:26,362][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:55:26,862][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:55:27,360][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:55:27,859][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:55:28,359][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:55:28,858][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:55:29,358][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:55:29,858][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:55:30,359][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:55:30,859][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:55:31,361][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:55:31,863][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:55:32,364][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:55:32,865][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:55:33,365][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:55:33,864][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:55:34,364][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:55:34,865][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:55:35,365][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:55:35,865][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:55:36,365][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:55:36,864][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:55:37,362][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:55:37,863][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:55:38,366][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:55:38,867][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:55:39,368][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:55:39,869][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:55:40,370][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:55:40,870][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:55:41,374][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:55:41,874][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:55:42,375][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:55:42,874][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:55:43,374][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:55:43,874][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:55:44,373][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:55:44,874][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:55:45,373][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:55:45,873][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:55:46,373][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:55:46,872][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:55:47,372][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:55:47,871][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:55:48,371][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:55:48,871][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:55:49,371][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:55:49,871][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:55:50,370][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:55:50,870][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:55:51,370][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:55:51,869][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:55:52,370][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:55:52,870][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:55:53,370][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:55:53,868][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:55:54,368][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:55:54,866][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:55:55,366][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:55:55,866][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:55:56,365][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:55:56,864][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:55:57,364][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21728 tokens. [2026-03-25 18:55:57,970][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.14%, Current % of VRAM taken: 60.50%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:04 [2026-03-25 18:55:58,691][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:55:58,694][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:55:58,695][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:55:59,382][__main__][INFO] - Iteration 145 took 1m 13s (8.47% Gen, 90.60% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 3m 50s. Estimated total time: 61h 24m 36s. Time estimates for 10 more iterations: 12m 16s, 100 more iterations: 2h 2m 49s, 500 more iterations: 10h 14m 6s. [2026-03-25 18:55:59,384][__main__][INFO] - Starting iteration 145. [2026-03-25 18:55:59,788][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:55:59,788][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:56:06,544][__main__][INFO] - Number of regex retries in iteration 145: 0 [2026-03-25 18:56:06,545][__main__][INFO] - agents played in iteration 145 are Bob, Alice [2026-03-25 18:56:07,480][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:56:08,057][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:56:08,516][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:56:09,024][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:56:09,526][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:56:10,028][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:56:10,531][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:56:11,033][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:56:11,537][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:56:12,040][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:56:12,540][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:56:13,042][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:56:13,543][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:56:14,044][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:56:14,545][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:56:15,047][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:56:15,547][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:56:16,047][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:56:16,548][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:56:17,048][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:56:17,548][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:56:18,049][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:56:18,550][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:56:19,051][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:56:19,552][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:56:20,053][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:56:20,554][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:56:21,054][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:56:21,554][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:56:22,054][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:56:22,554][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:56:23,053][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:56:23,554][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:56:24,053][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:56:24,552][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:56:25,053][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:56:25,552][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:56:26,053][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:56:26,552][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:56:27,052][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:56:27,552][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:56:28,053][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:56:28,554][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:56:29,054][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:56:29,555][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:56:30,055][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:56:30,556][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:56:31,057][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:56:31,558][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:56:32,059][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:56:32,559][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:56:33,058][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:56:33,558][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:56:34,057][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:56:34,556][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:56:35,055][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:56:35,554][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:56:36,054][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:56:36,555][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:56:37,057][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:56:37,559][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:56:38,059][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:56:38,560][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:56:39,061][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:56:39,562][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:56:40,063][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:56:40,565][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:56:41,066][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:56:41,568][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:56:42,069][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:56:42,571][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:56:43,074][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:56:43,575][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:56:44,076][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:56:44,576][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:56:45,076][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:56:45,576][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:56:46,076][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:56:46,576][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:56:47,076][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:56:47,576][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:56:48,077][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:56:48,577][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:56:49,077][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:56:49,578][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:56:50,078][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:56:50,578][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:56:51,078][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:56:51,579][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:56:52,079][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:56:52,579][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:56:53,080][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:56:53,580][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:56:54,080][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:56:54,580][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:56:55,081][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:56:55,583][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:56:56,085][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:56:56,584][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:56:57,084][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:56:57,585][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:56:58,085][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:56:58,585][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:56:59,085][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:56:59,584][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:57:00,084][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:57:00,585][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:57:01,086][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:57:01,587][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:57:02,088][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:57:02,588][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:57:03,090][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:57:03,590][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:57:04,091][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:57:04,591][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:57:05,090][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:57:05,590][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:57:06,090][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:57:06,590][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:57:07,090][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:57:07,589][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:57:08,090][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:57:08,591][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:57:09,091][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:57:09,591][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:57:10,092][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:57:10,592][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:57:11,091][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:57:11,594][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:57:12,095][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21739 tokens. [2026-03-25 18:57:12,701][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 18:57:13,437][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:57:13,439][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:57:13,440][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:57:14,089][__main__][INFO] - Iteration 146 took 1m 14s (9.09% Gen, 90.03% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 33m 4s. Estimated total time: 61h 55m 4s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 50s, 500 more iterations: 10h 19m 10s. [2026-03-25 18:57:14,091][__main__][INFO] - Starting iteration 146. [2026-03-25 18:57:14,489][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:57:14,490][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:57:20,802][__main__][INFO] - Number of regex retries in iteration 146: 0 [2026-03-25 18:57:20,803][__main__][INFO] - agents played in iteration 146 are Bob, Alice [2026-03-25 18:57:21,724][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:57:22,301][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:57:22,758][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:57:23,264][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:57:23,765][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:57:24,266][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:57:24,768][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:57:25,269][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:57:25,770][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:57:26,271][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:57:26,772][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:57:27,272][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:57:27,773][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:57:28,274][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:57:28,775][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:57:29,276][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:57:29,778][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:57:30,278][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:57:30,778][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:57:31,280][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:57:31,780][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:57:32,281][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:57:32,781][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:57:33,281][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:57:33,781][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:57:34,284][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:57:34,786][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:57:35,288][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:57:35,788][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:57:36,289][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:57:36,790][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:57:37,291][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:57:37,792][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:57:38,293][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:57:38,793][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:57:39,292][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:57:39,791][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:57:40,291][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:57:40,790][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:57:41,292][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:57:41,794][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:57:42,294][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:57:42,791][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:57:43,289][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:57:43,788][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:57:44,287][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:57:44,787][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:57:45,286][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:57:45,785][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:57:46,283][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:57:46,785][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:57:47,286][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:57:47,786][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:57:48,287][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:57:48,787][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:57:49,288][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:57:49,788][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:57:50,289][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:57:50,789][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:57:51,290][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:57:51,790][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:57:52,290][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:57:52,790][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:57:53,291][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:57:53,791][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:57:54,291][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:57:54,791][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:57:55,291][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:57:55,793][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:57:56,293][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:57:56,792][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:57:57,293][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:57:57,793][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:57:58,293][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:57:58,794][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:57:59,295][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:57:59,795][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:58:00,296][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:58:00,796][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:58:01,297][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:58:01,798][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:58:02,299][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:58:02,800][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:58:03,300][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:58:03,799][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:58:04,299][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:58:04,799][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:58:05,298][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:58:05,798][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:58:06,299][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:58:06,799][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:58:07,302][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:58:07,804][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:58:08,307][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:58:08,808][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:58:09,309][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:58:09,811][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:58:10,312][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:58:10,812][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:58:11,314][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:58:11,815][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:58:12,316][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:58:12,815][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:58:13,315][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:58:13,814][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:58:14,314][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:58:14,811][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:58:15,310][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:58:15,808][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:58:16,307][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:58:16,806][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:58:17,303][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:58:17,801][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:58:18,300][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:58:18,802][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:58:19,304][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:58:19,805][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:58:20,305][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:58:20,806][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:58:21,307][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:58:21,808][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:58:22,309][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:58:22,810][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:58:23,311][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:58:23,812][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:58:24,312][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:58:24,813][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:58:25,314][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:58:25,814][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:58:26,315][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-25 18:58:26,922][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-25 18:58:27,643][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:58:27,645][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:58:27,647][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:58:28,281][__main__][INFO] - Iteration 147 took 1m 13s (8.56% Gen, 90.58% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 6m 21s. Estimated total time: 61h 29m 36s. Time estimates for 10 more iterations: 12m 17s, 100 more iterations: 2h 2m 59s, 500 more iterations: 10h 14m 56s. [2026-03-25 18:58:28,283][__main__][INFO] - Starting iteration 147. [2026-03-25 18:58:28,684][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:58:28,685][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:58:29,277][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:58:31,896][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:58:34,981][__main__][INFO] - Number of regex retries in iteration 147: 2 [2026-03-25 18:58:34,982][__main__][INFO] - agents played in iteration 147 are Bob, Alice [2026-03-25 18:58:35,915][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:58:36,490][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:58:36,948][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:58:37,454][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:58:37,955][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:58:38,456][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:58:38,957][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:58:39,457][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:58:39,957][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:58:40,458][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:58:40,958][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:58:41,461][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:58:41,961][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:58:42,464][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:58:42,965][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:58:43,466][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:58:43,966][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:58:44,468][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:58:44,968][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 18:58:45,469][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 18:58:45,970][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 18:58:46,471][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 18:58:46,972][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 18:58:47,472][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 18:58:47,972][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 18:58:48,474][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 18:58:48,974][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 18:58:49,474][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 18:58:49,975][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 18:58:50,474][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 18:58:50,975][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 18:58:51,475][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 18:58:51,974][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 18:58:52,474][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 18:58:52,975][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 18:58:53,477][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 18:58:53,977][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 18:58:54,477][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 18:58:54,978][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 18:58:55,479][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 18:58:55,980][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 18:58:56,481][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 18:58:56,982][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 18:58:57,482][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 18:58:57,983][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 18:58:58,484][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 18:58:58,986][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 18:58:59,487][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 18:58:59,988][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 18:59:00,488][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 18:59:00,989][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 18:59:01,490][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 18:59:01,990][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 18:59:02,491][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 18:59:02,992][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 18:59:03,492][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 18:59:03,992][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 18:59:04,492][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 18:59:04,993][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 18:59:05,493][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 18:59:05,994][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 18:59:06,495][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 18:59:06,995][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 18:59:07,496][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 18:59:07,996][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 18:59:08,496][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 18:59:08,996][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 18:59:09,496][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 18:59:09,997][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 18:59:10,497][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 18:59:10,997][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 18:59:11,500][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 18:59:12,000][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 18:59:12,500][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 18:59:13,002][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 18:59:13,502][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 18:59:14,001][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 18:59:14,502][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 18:59:15,003][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 18:59:15,506][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 18:59:16,006][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 18:59:16,508][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 18:59:17,007][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 18:59:17,507][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 18:59:18,007][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 18:59:18,508][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 18:59:19,008][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 18:59:19,508][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 18:59:20,008][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 18:59:20,509][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 18:59:21,009][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 18:59:21,510][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 18:59:22,011][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 18:59:22,513][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 18:59:23,014][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 18:59:23,514][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 18:59:24,014][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 18:59:24,514][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 18:59:25,014][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 18:59:25,515][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 18:59:26,016][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 18:59:26,517][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 18:59:27,017][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 18:59:27,518][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 18:59:28,018][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 18:59:28,519][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 18:59:29,020][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 18:59:29,521][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 18:59:30,021][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 18:59:30,521][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 18:59:31,021][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 18:59:31,522][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 18:59:32,025][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 18:59:32,526][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 18:59:33,028][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 18:59:33,530][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 18:59:34,030][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 18:59:34,531][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 18:59:35,031][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 18:59:35,531][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 18:59:36,032][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 18:59:36,532][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 18:59:37,034][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 18:59:37,535][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 18:59:38,036][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 18:59:38,536][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 18:59:39,036][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 18:59:39,536][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 18:59:40,037][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 18:59:40,538][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 18:59:41,151][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:04 [2026-03-25 18:59:41,876][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 18:59:41,878][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 18:59:41,880][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 18:59:42,726][__main__][INFO] - Iteration 148 took 1m 14s (8.50% Gen, 90.35% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 17m 38s. Estimated total time: 61h 42m 7s. Time estimates for 10 more iterations: 12m 20s, 100 more iterations: 2h 3m 24s, 500 more iterations: 10h 17m 1s. [2026-03-25 18:59:42,728][__main__][INFO] - Starting iteration 148. [2026-03-25 18:59:43,127][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 18:59:43,128][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 18:59:43,743][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 18:59:49,641][__main__][INFO] - Number of regex retries in iteration 148: 1 [2026-03-25 18:59:49,642][__main__][INFO] - agents played in iteration 148 are Bob, Alice [2026-03-25 18:59:50,591][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 18:59:51,175][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 18:59:51,633][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 18:59:52,140][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 18:59:52,642][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 18:59:53,144][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 18:59:53,645][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 18:59:54,147][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 18:59:54,648][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 18:59:55,149][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 18:59:55,651][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 18:59:56,151][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 18:59:56,652][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 18:59:57,152][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 18:59:57,653][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 18:59:58,154][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 18:59:58,654][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 18:59:59,155][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 18:59:59,655][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:00:00,155][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:00:00,655][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:00:01,155][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:00:01,655][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:00:02,154][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:00:02,655][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:00:03,154][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:00:03,654][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:00:04,154][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:00:04,654][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:00:05,155][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:00:05,655][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:00:06,156][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:00:06,656][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:00:07,156][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:00:07,657][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:00:08,157][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:00:08,658][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:00:09,159][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:00:09,660][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:00:10,160][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:00:10,661][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:00:11,164][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:00:11,667][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:00:12,167][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:00:12,668][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:00:13,168][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:00:13,669][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:00:14,171][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:00:14,672][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:00:15,172][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:00:15,673][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:00:16,173][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:00:16,670][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:00:17,171][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:00:17,672][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:00:18,173][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:00:18,673][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:00:19,174][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:00:19,674][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:00:20,174][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:00:20,674][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:00:21,174][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:00:21,675][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:00:22,176][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:00:22,676][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:00:23,176][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:00:23,676][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:00:24,176][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:00:24,676][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:00:25,177][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:00:25,677][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:00:26,177][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:00:26,677][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:00:27,178][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:00:27,679][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:00:28,179][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:00:28,680][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:00:29,181][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:00:29,681][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:00:30,182][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:00:30,686][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:00:31,186][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:00:31,687][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:00:32,187][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:00:32,687][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:00:33,189][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:00:33,689][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:00:34,190][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:00:34,693][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:00:35,193][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:00:35,694][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:00:36,193][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:00:36,693][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:00:37,194][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:00:37,694][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:00:38,195][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:00:38,695][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:00:39,196][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:00:39,696][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:00:40,196][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:00:40,695][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:00:41,197][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:00:41,699][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:00:42,200][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:00:42,700][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:00:43,200][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:00:43,702][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:00:44,203][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:00:44,704][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:00:45,205][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:00:45,706][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:00:46,207][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:00:46,707][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:00:47,208][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:00:47,708][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:00:48,208][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:00:48,710][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:00:49,211][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:00:49,712][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:00:50,213][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:00:50,714][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:00:51,215][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:00:51,715][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:00:52,216][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:00:52,716][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:00:53,217][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:00:53,717][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:00:54,217][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:00:54,718][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:00:55,220][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21639 tokens. [2026-03-25 19:00:55,835][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-25 19:00:56,564][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:00:56,566][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:00:56,567][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:00:57,201][__main__][INFO] - Iteration 149 took 1m 14s (8.79% Gen, 90.35% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 17m 59s. Estimated total time: 61h 43m 43s. Time estimates for 10 more iterations: 12m 20s, 100 more iterations: 2h 3m 27s, 500 more iterations: 10h 17m 17s. [2026-03-25 19:00:57,203][__main__][INFO] - Starting iteration 149. [2026-03-25 19:00:57,603][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 19:00:57,604][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:01:03,938][__main__][INFO] - Number of regex retries in iteration 149: 0 [2026-03-25 19:01:03,939][__main__][INFO] - agents played in iteration 149 are Bob, Alice [2026-03-25 19:01:04,864][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:01:05,446][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:01:05,903][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:01:06,408][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:01:06,910][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:01:07,413][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:01:07,914][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:01:08,415][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:01:08,916][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:01:09,417][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:01:09,915][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:01:10,414][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:01:10,912][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:01:11,414][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:01:11,912][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:01:12,411][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:01:12,910][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:01:13,409][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:01:13,912][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:01:14,413][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:01:14,914][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:01:15,415][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:01:15,916][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:01:16,417][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:01:16,917][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:01:17,417][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:01:17,917][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:01:18,418][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:01:18,918][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:01:19,419][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:01:19,920][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:01:20,421][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:01:20,921][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:01:21,422][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:01:21,925][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:01:22,426][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:01:22,928][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:01:23,430][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:01:23,931][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:01:24,432][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:01:24,933][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:01:25,434][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:01:25,936][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:01:26,436][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:01:26,937][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:01:27,437][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:01:27,939][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:01:28,440][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:01:28,941][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:01:29,443][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:01:29,943][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:01:30,444][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:01:30,945][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:01:31,446][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:01:31,947][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:01:32,448][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:01:32,949][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:01:33,450][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:01:33,950][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:01:34,451][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:01:34,952][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:01:35,453][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:01:35,953][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:01:36,454][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:01:36,953][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:01:37,453][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:01:37,953][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:01:38,453][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:01:38,954][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:01:39,455][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:01:39,956][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:01:40,456][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:01:40,956][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:01:41,458][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:01:41,956][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:01:42,455][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:01:42,953][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:01:43,452][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:01:43,950][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:01:44,449][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:01:44,948][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:01:45,446][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:01:45,948][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:01:46,449][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:01:46,951][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:01:47,451][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:01:47,952][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:01:48,454][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:01:48,954][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:01:49,455][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:01:49,955][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:01:50,457][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:01:50,956][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:01:51,456][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:01:51,956][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:01:52,456][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:01:52,956][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:01:53,456][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:01:53,959][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:01:54,460][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:01:54,962][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:01:55,464][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:01:55,966][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:01:56,467][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:01:56,969][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:01:57,470][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:01:57,971][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:01:58,472][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:01:58,973][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:01:59,474][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:01:59,974][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:02:00,474][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:02:00,974][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:02:01,474][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:02:01,974][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:02:02,474][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:02:02,975][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:02:03,475][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:02:03,975][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:02:04,474][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:02:04,975][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:02:05,475][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:02:05,977][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:02:06,477][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:02:06,978][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:02:07,478][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:02:07,980][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:02:08,482][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:02:08,984][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:02:09,486][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21748 tokens. [2026-03-25 19:02:10,102][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 19:02:10,823][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:02:10,826][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:02:10,827][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:02:11,432][__main__][INFO] - Iteration 150 took 1m 13s (8.58% Gen, 90.60% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 4m 29s. Estimated total time: 61h 31m 27s. Time estimates for 10 more iterations: 12m 18s, 100 more iterations: 2h 3m 2s, 500 more iterations: 10h 15m 14s. [2026-03-25 19:02:11,434][__main__][INFO] - Starting iteration 150. [2026-03-25 19:02:11,839][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 2 and human policies 1. [2026-03-25 19:02:11,839][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:02:18,060][__main__][INFO] - Number of regex retries in iteration 150: 0 [2026-03-25 19:02:18,061][__main__][INFO] - agents played in iteration 150 are Bob, Alice [2026-03-25 19:02:19,003][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:02:19,581][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:02:20,038][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:02:20,542][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:02:21,043][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:02:21,543][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:02:22,042][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:02:22,544][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:02:23,045][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:02:23,545][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:02:24,047][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:02:24,548][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:02:25,048][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:02:25,549][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:02:26,050][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:02:26,550][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:02:27,051][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:02:27,551][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:02:28,048][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:02:28,547][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:02:29,047][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:02:29,547][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:02:30,046][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:02:30,545][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:02:31,044][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:02:31,542][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:02:32,044][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:02:32,545][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:02:33,047][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:02:33,547][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:02:34,048][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:02:34,548][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:02:35,049][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:02:35,550][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:02:36,052][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:02:36,554][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:02:37,059][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:02:37,561][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:02:38,061][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:02:38,561][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:02:39,064][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:02:39,565][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:02:40,066][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:02:40,566][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:02:41,067][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:02:41,569][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:02:42,070][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:02:42,571][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:02:43,072][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:02:43,572][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:02:44,072][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:02:44,571][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:02:45,072][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:02:45,571][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:02:46,071][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:02:46,571][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:02:47,071][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:02:47,571][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:02:48,071][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:02:48,570][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:02:49,070][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:02:49,570][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:02:50,071][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:02:50,571][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:02:51,071][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:02:51,571][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:02:52,071][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:02:52,572][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:02:53,072][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:02:53,573][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:02:54,073][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:02:54,573][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:02:55,072][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:02:55,572][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:02:56,073][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:02:56,573][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:02:57,074][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:02:57,574][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:02:58,075][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:02:58,575][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:02:59,076][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:02:59,576][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:03:00,074][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:03:00,573][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:03:01,071][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:03:01,569][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:03:02,068][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:03:02,566][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:03:03,065][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:03:03,565][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:03:04,066][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:03:04,567][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:03:05,067][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:03:05,568][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:03:06,068][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:03:06,569][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:03:07,070][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:03:07,570][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:03:08,071][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:03:08,571][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:03:09,071][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:03:09,571][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:03:10,071][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:03:10,572][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:03:11,074][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:03:11,576][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:03:12,077][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:03:12,576][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:03:13,076][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:03:13,577][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:03:14,077][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:03:14,578][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:03:15,077][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:03:15,578][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:03:16,078][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:03:16,578][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:03:17,077][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:03:17,578][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:03:18,078][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:03:18,577][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:03:19,077][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:03:19,576][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:03:20,075][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:03:20,576][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:03:21,076][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:03:21,576][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:03:22,076][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:03:22,577][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:03:23,077][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:03:23,577][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21740 tokens. [2026-03-25 19:03:24,186][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:04 [2026-03-25 19:03:24,917][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:03:24,919][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:03:24,921][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:03:26,472][__main__][INFO] - Iteration 151 took 1m 14s (8.34% Gen, 89.58% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 43m 26s. Estimated total time: 62h 11m 40s. Time estimates for 10 more iterations: 12m 26s, 100 more iterations: 2h 4m 23s, 500 more iterations: 10h 21m 56s. [2026-03-25 19:03:26,474][__main__][INFO] - Starting iteration 151. [2026-03-25 19:03:26,874][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:03:26,874][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:03:27,453][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:03:29,612][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:03:33,271][__main__][INFO] - Number of regex retries in iteration 151: 2 [2026-03-25 19:03:33,271][__main__][INFO] - agents played in iteration 151 are Bob, Alice [2026-03-25 19:03:34,194][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:03:34,774][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:03:35,231][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:03:35,735][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:03:36,235][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:03:36,737][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:03:37,237][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:03:37,738][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:03:38,239][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:03:38,739][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:03:39,240][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:03:39,739][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:03:40,240][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:03:40,740][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:03:41,243][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:03:41,744][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:03:42,244][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:03:42,746][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:03:43,246][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:03:43,747][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:03:44,247][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:03:44,748][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:03:45,248][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:03:45,748][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:03:46,249][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:03:46,749][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:03:47,249][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:03:47,748][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:03:48,247][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:03:48,747][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:03:49,246][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:03:49,745][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:03:50,245][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:03:50,745][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:03:51,247][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:03:51,749][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:03:52,250][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:03:52,751][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:03:53,252][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:03:53,753][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:03:54,254][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:03:54,755][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:03:55,256][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:03:55,758][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:03:56,258][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:03:56,761][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:03:57,261][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:03:57,762][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:03:58,263][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:03:58,763][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:03:59,263][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:03:59,762][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:04:00,264][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:04:00,765][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:04:01,265][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:04:01,764][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:04:02,264][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:04:02,763][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:04:03,262][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:04:03,764][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:04:04,264][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:04:04,765][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:04:05,265][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:04:05,765][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:04:06,265][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:04:06,766][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:04:07,268][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:04:07,769][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:04:08,270][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:04:08,770][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:04:09,270][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:04:09,770][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:04:10,270][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:04:10,770][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:04:11,273][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:04:11,774][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:04:12,274][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:04:12,774][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:04:13,273][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:04:13,773][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:04:14,274][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:04:14,774][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:04:15,274][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:04:15,773][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:04:16,273][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:04:16,772][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:04:17,273][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:04:17,772][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:04:18,273][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:04:18,773][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:04:19,272][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:04:19,771][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:04:20,269][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:04:20,768][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:04:21,266][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:04:21,765][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:04:22,265][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:04:22,764][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:04:23,265][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:04:23,767][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:04:24,268][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:04:24,769][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:04:25,270][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:04:25,771][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:04:26,272][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:04:26,773][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:04:27,272][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:04:27,773][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:04:28,273][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:04:28,774][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:04:29,274][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:04:29,774][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:04:30,274][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:04:30,774][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:04:31,273][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:04:31,773][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:04:32,273][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:04:32,773][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:04:33,272][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:04:33,772][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:04:34,271][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:04:34,771][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:04:35,272][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:04:35,772][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:04:36,272][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:04:36,772][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:04:37,272][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:04:37,771][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:04:38,274][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:04:38,774][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21747 tokens. [2026-03-25 19:04:39,386][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 19:04:40,115][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:04:40,118][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:04:40,119][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:04:40,789][__main__][INFO] - Iteration 152 took 1m 13s (8.65% Gen, 90.44% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 6m 21s. Estimated total time: 61h 35m 48s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 11s, 500 more iterations: 10h 15m 58s. [2026-03-25 19:04:40,792][__main__][INFO] - Starting iteration 152. [2026-03-25 19:04:41,196][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:04:41,197][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:04:41,788][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:04:45,688][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:04:47,835][__main__][INFO] - Number of regex retries in iteration 152: 2 [2026-03-25 19:04:47,835][__main__][INFO] - agents played in iteration 152 are Bob, Alice [2026-03-25 19:04:48,778][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:04:49,361][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:04:49,819][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:04:50,324][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:04:50,826][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:04:51,326][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:04:51,826][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:04:52,325][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:04:52,825][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:04:53,326][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:04:53,828][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:04:54,329][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:04:54,831][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:04:55,332][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:04:55,833][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:04:56,333][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:04:56,834][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:04:57,335][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:04:57,835][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:04:58,336][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:04:58,836][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:04:59,338][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:04:59,838][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:05:00,339][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:05:00,839][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:05:01,339][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:05:01,840][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:05:02,340][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:05:02,842][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:05:03,343][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:05:03,845][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:05:04,346][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:05:04,847][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:05:05,348][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:05:05,848][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:05:06,349][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:05:06,850][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:05:07,351][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:05:07,851][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:05:08,352][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:05:08,852][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:05:09,353][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:05:09,853][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:05:10,353][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:05:10,853][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:05:11,356][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:05:11,857][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:05:12,357][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:05:12,858][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:05:13,358][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:05:13,860][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:05:14,360][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:05:14,860][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:05:15,359][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:05:15,860][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:05:16,360][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:05:16,860][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:05:17,361][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:05:17,864][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:05:18,366][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:05:18,868][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:05:19,369][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:05:19,870][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:05:20,371][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:05:20,872][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:05:21,373][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:05:21,872][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:05:22,372][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:05:22,872][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:05:23,372][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:05:23,871][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:05:24,371][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:05:24,871][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:05:25,370][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:05:25,871][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:05:26,371][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:05:26,872][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:05:27,373][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:05:27,873][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:05:28,373][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:05:28,873][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:05:29,374][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:05:29,874][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:05:30,375][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:05:30,875][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:05:31,375][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:05:31,875][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:05:32,374][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:05:32,874][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:05:33,374][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:05:33,874][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:05:34,374][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:05:34,873][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:05:35,373][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:05:35,872][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:05:36,373][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:05:36,874][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:05:37,377][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:05:37,877][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:05:38,378][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:05:38,879][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:05:39,382][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:05:39,884][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:05:40,385][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:05:40,886][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:05:41,390][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:05:41,891][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:05:42,392][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:05:42,893][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:05:43,395][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:05:43,895][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:05:44,396][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:05:44,896][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:05:45,396][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:05:45,897][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:05:46,397][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:05:46,897][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:05:47,397][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:05:47,897][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:05:48,396][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:05:48,896][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:05:49,396][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:05:49,897][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:05:50,398][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:05:50,899][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:05:51,400][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:05:51,900][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:05:52,402][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:05:52,904][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:05:53,406][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 19:05:54,030][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-25 19:05:54,751][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:05:54,754][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:05:54,755][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:05:55,397][__main__][INFO] - Iteration 153 took 1m 14s (8.95% Gen, 90.19% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 19m 20s. Estimated total time: 61h 50m 2s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 40s, 500 more iterations: 10h 18m 20s. [2026-03-25 19:05:55,399][__main__][INFO] - Starting iteration 153. [2026-03-25 19:05:55,800][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:05:55,801][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:06:02,245][__main__][INFO] - Number of regex retries in iteration 153: 0 [2026-03-25 19:06:02,245][__main__][INFO] - agents played in iteration 153 are Bob, Alice [2026-03-25 19:06:03,167][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:06:03,751][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:06:04,209][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:06:04,713][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:06:05,214][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:06:05,714][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:06:06,215][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:06:06,715][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:06:07,216][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:06:07,716][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:06:08,218][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:06:08,720][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:06:09,221][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:06:09,722][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:06:10,223][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:06:10,723][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:06:11,227][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:06:11,729][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:06:12,230][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:06:12,731][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:06:13,232][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:06:13,731][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:06:14,232][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:06:14,732][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:06:15,234][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:06:15,734][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:06:16,232][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:06:16,729][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:06:17,225][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:06:17,722][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:06:18,218][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:06:18,714][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:06:19,212][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:06:19,709][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:06:20,212][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:06:20,715][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:06:21,215][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:06:21,716][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:06:22,218][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:06:22,719][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:06:23,220][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:06:23,722][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:06:24,222][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:06:24,722][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:06:25,222][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:06:25,724][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:06:26,224][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:06:26,724][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:06:27,224][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:06:27,723][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:06:28,224][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:06:28,726][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:06:29,228][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:06:29,729][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:06:30,231][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:06:30,732][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:06:31,233][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:06:31,734][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:06:32,234][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:06:32,734][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:06:33,235][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:06:33,735][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:06:34,236][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:06:34,736][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:06:35,237][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:06:35,738][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:06:36,238][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:06:36,738][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:06:37,238][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:06:37,739][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:06:38,238][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:06:38,738][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:06:39,238][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:06:39,738][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:06:40,239][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:06:40,741][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:06:41,243][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:06:41,743][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:06:42,246][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:06:42,748][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:06:43,248][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:06:43,749][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:06:44,250][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:06:44,751][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:06:45,251][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:06:45,752][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:06:46,253][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:06:46,753][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:06:47,254][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:06:47,754][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:06:48,251][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:06:48,748][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:06:49,245][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:06:49,743][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:06:50,240][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:06:50,738][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:06:51,234][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:06:51,731][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:06:52,231][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:06:52,732][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:06:53,233][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:06:53,734][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:06:54,235][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:06:54,736][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:06:55,237][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:06:55,737][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:06:56,236][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:06:56,735][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:06:57,233][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:06:57,732][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:06:58,231][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:06:58,730][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:06:59,229][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:06:59,729][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:07:00,229][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:07:00,731][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:07:01,233][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:07:01,734][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:07:02,235][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:07:02,735][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:07:03,236][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:07:03,737][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:07:04,237][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:07:04,738][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:07:05,238][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:07:05,739][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:07:06,238][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:07:06,739][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:07:07,242][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:07:07,744][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 19:07:08,358][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 19:07:09,078][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:07:09,080][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:07:09,081][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:07:09,691][__main__][INFO] - Iteration 154 took 1m 13s (8.72% Gen, 90.45% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 2m 37s. Estimated total time: 61h 34m 34s. Time estimates for 10 more iterations: 12m 18s, 100 more iterations: 2h 3m 9s, 500 more iterations: 10h 15m 45s. [2026-03-25 19:07:09,693][__main__][INFO] - Starting iteration 154. [2026-03-25 19:07:10,098][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:07:10,098][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:07:12,319][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 books, 10 balls, 10 hats did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:07:16,548][__main__][INFO] - Number of regex retries in iteration 154: 1 [2026-03-25 19:07:16,548][__main__][INFO] - agents played in iteration 154 are Bob, Alice [2026-03-25 19:07:17,476][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:07:18,323][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:07:18,780][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:07:19,286][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:07:19,787][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:07:20,287][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:07:20,788][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:07:21,289][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:07:21,790][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:07:22,291][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:07:22,793][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:07:23,294][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:07:23,795][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:07:24,296][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:07:24,796][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:07:25,296][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:07:25,797][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:07:26,298][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:07:26,798][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:07:27,297][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:07:27,796][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:07:28,295][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:07:28,794][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:07:29,294][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:07:29,795][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:07:30,294][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:07:30,794][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:07:31,294][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:07:31,794][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:07:32,294][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:07:32,795][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:07:33,297][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:07:33,796][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:07:34,297][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:07:34,797][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:07:35,298][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:07:35,800][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:07:36,301][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:07:36,803][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:07:37,305][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:07:37,806][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:07:38,307][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:07:38,808][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:07:39,308][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:07:39,809][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:07:40,306][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:07:40,806][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:07:41,310][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:07:41,811][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:07:42,312][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:07:42,817][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:07:43,319][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:07:43,821][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:07:44,323][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:07:44,828][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:07:45,330][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:07:45,832][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:07:46,334][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:07:46,836][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:07:47,337][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:07:47,838][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:07:48,339][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:07:48,840][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:07:49,342][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:07:49,843][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:07:50,344][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:07:50,845][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:07:51,345][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:07:51,846][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:07:52,346][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:07:52,846][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:07:53,347][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:07:53,848][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:07:54,348][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:07:54,848][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:07:55,349][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:07:55,850][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:07:56,351][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:07:56,851][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:07:57,351][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:07:57,852][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:07:58,354][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:07:58,853][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:07:59,354][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:07:59,854][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:08:00,353][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:08:00,853][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:08:01,353][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:08:01,853][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:08:02,353][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:08:02,853][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:08:03,354][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:08:03,854][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:08:04,355][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:08:04,855][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:08:05,355][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:08:05,855][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:08:06,355][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:08:06,855][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:08:07,356][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:08:07,856][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:08:08,357][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:08:08,857][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:08:09,357][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:08:09,858][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:08:10,358][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:08:10,858][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:08:11,361][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:08:11,862][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:08:12,364][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:08:12,863][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:08:13,363][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:08:13,863][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:08:14,365][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:08:14,867][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:08:15,368][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:08:15,870][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:08:16,371][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:08:16,872][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:08:17,374][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:08:17,875][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:08:18,377][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:08:18,877][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:08:19,377][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:08:19,877][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:08:20,378][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:08:20,878][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:08:21,380][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:08:21,880][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:08:22,381][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21724 tokens. [2026-03-25 19:08:23,000][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:04 [2026-03-25 19:08:23,723][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:08:23,725][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:08:23,727][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:08:24,333][__main__][INFO] - Iteration 155 took 1m 14s (8.69% Gen, 90.49% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 58h 18m 36s. Estimated total time: 61h 51m 47s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 43s, 500 more iterations: 10h 18m 37s. [2026-03-25 19:08:24,335][__main__][INFO] - Starting iteration 155. [2026-03-25 19:08:24,737][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:08:24,738][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:08:25,329][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:08:31,103][__main__][INFO] - Number of regex retries in iteration 155: 1 [2026-03-25 19:08:31,104][__main__][INFO] - agents played in iteration 155 are Bob, Alice [2026-03-25 19:08:32,022][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:08:32,600][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:08:33,059][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:08:33,566][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:08:34,068][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:08:34,570][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:08:35,072][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:08:35,574][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:08:36,075][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:08:36,577][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:08:37,078][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:08:37,579][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:08:38,079][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:08:38,579][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:08:39,079][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:08:39,580][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:08:40,080][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:08:40,580][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:08:41,082][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:08:41,585][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:08:42,088][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:08:42,590][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:08:43,092][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:08:43,595][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:08:44,096][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:08:44,598][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:08:45,100][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:08:45,604][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:08:46,106][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:08:46,608][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:08:47,110][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:08:47,612][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:08:48,115][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:08:48,617][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:08:49,118][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:08:49,618][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:08:50,117][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:08:50,617][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:08:51,117][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:08:51,617][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:08:52,118][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:08:52,618][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:08:53,118][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:08:53,617][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:08:54,117][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:08:54,617][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:08:55,117][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:08:55,618][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:08:56,118][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:08:56,618][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:08:57,118][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:08:57,620][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:08:58,121][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:08:58,623][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:08:59,125][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:08:59,626][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:09:00,128][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:09:00,630][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:09:01,132][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:09:01,634][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:09:02,135][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:09:02,637][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:09:03,139][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:09:03,640][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:09:04,142][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:09:04,644][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:09:05,147][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:09:05,650][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:09:06,154][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:09:06,656][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:09:07,158][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:09:07,661][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:09:08,163][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:09:08,666][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:09:09,167][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:09:09,668][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:09:10,169][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:09:10,670][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:09:11,171][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:09:11,673][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:09:12,173][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:09:12,674][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:09:13,176][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:09:13,679][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:09:14,181][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:09:14,683][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:09:15,186][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:09:15,688][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:09:16,192][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:09:16,694][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:09:17,197][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:09:17,700][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:09:18,203][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:09:18,706][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:09:19,210][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:09:19,712][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:09:20,214][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:09:20,717][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:09:21,219][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:09:21,721][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:09:22,223][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:09:22,725][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:09:23,227][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:09:23,729][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:09:24,232][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:09:24,734][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:09:25,235][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:09:25,736][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:09:26,237][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:09:26,738][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:09:27,239][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:09:27,740][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:09:28,241][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:09:28,742][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:09:29,244][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:09:29,746][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:09:30,248][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:09:30,750][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:09:31,252][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:09:31,753][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:09:32,255][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:09:32,756][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:09:33,257][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:09:33,759][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:09:34,261][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:09:34,763][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:09:35,264][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:09:35,766][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:09:36,268][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:09:36,770][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 19:09:37,384][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 19:09:38,120][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:09:38,122][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:09:38,124][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:09:38,782][__main__][INFO] - Iteration 156 took 1m 14s (8.60% Gen, 90.51% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 58h 7m 49s. Estimated total time: 61h 42m 14s. Time estimates for 10 more iterations: 12m 20s, 100 more iterations: 2h 3m 24s, 500 more iterations: 10h 17m 2s. [2026-03-25 19:09:38,783][__main__][INFO] - Starting iteration 156. [2026-03-25 19:09:39,183][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:09:39,184][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:09:43,362][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:09:43,989][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:09:45,402][__main__][INFO] - Number of regex retries in iteration 156: 2 [2026-03-25 19:09:45,403][__main__][INFO] - agents played in iteration 156 are Bob, Alice [2026-03-25 19:09:46,341][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:09:46,914][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:09:47,369][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:09:47,873][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:09:48,373][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:09:48,873][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:09:49,374][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:09:49,874][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:09:50,373][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:09:50,873][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:09:51,374][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:09:51,875][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:09:52,375][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:09:52,877][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:09:53,377][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:09:53,877][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:09:54,377][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:09:54,877][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:09:55,377][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:09:55,876][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:09:56,376][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:09:56,875][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:09:57,374][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:09:57,874][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:09:58,373][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:09:58,873][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:09:59,373][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:09:59,873][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:10:00,372][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:10:00,872][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:10:01,371][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:10:01,871][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:10:02,371][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:10:02,871][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:10:03,373][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:10:03,874][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:10:04,375][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:10:04,875][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:10:05,375][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:10:05,875][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:10:06,375][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:10:06,877][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:10:07,376][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:10:07,875][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:10:08,373][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:10:08,871][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:10:09,370][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:10:09,869][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:10:10,368][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:10:10,867][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:10:11,370][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:10:11,871][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:10:12,371][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:10:12,871][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:10:13,371][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:10:13,873][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:10:14,373][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:10:14,873][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:10:15,373][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:10:15,873][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:10:16,374][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:10:16,876][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:10:17,377][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:10:17,877][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:10:18,378][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:10:18,879][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:10:19,380][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:10:19,881][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:10:20,383][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:10:20,885][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:10:21,386][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:10:21,887][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:10:22,388][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:10:22,889][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:10:23,392][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:10:23,893][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:10:24,395][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:10:24,896][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:10:25,398][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:10:25,900][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:10:26,403][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:10:26,905][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:10:27,406][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:10:27,907][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:10:28,407][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:10:28,908][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:10:29,408][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:10:29,909][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:10:30,409][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:10:30,910][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:10:31,411][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:10:31,912][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:10:32,413][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:10:32,914][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:10:33,415][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:10:33,917][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:10:34,417][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:10:34,918][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:10:35,420][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:10:35,923][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:10:36,425][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:10:36,927][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:10:37,429][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:10:37,932][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:10:38,434][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:10:38,936][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:10:39,435][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:10:39,934][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:10:40,433][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:10:40,933][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:10:41,435][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:10:41,934][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:10:42,434][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:10:42,933][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:10:43,435][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:10:43,935][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:10:44,436][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:10:44,937][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:10:45,440][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:10:45,942][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:10:46,443][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:10:46,945][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:10:47,448][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:10:47,950][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:10:48,451][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:10:48,953][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:10:49,454][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:10:49,956][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:10:50,458][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:10:50,960][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21689 tokens. [2026-03-25 19:10:51,575][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-25 19:10:52,309][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:10:52,312][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:10:52,314][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:10:52,935][__main__][INFO] - Iteration 157 took 1m 13s (8.43% Gen, 90.72% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 51m 57s. Estimated total time: 61h 27m 37s. Time estimates for 10 more iterations: 12m 17s, 100 more iterations: 2h 2m 55s, 500 more iterations: 10h 14m 36s. [2026-03-25 19:10:52,938][__main__][INFO] - Starting iteration 157. [2026-03-25 19:10:53,339][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:10:53,339][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:10:53,922][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:11:00,147][__main__][INFO] - Number of regex retries in iteration 157: 1 [2026-03-25 19:11:00,147][__main__][INFO] - agents played in iteration 157 are Bob, Alice [2026-03-25 19:11:01,074][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:11:01,657][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:11:02,112][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:11:02,618][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:11:03,117][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:11:03,616][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:11:04,115][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:11:04,614][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:11:05,113][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:11:05,612][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:11:06,116][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:11:06,617][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:11:07,118][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:11:07,619][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:11:08,120][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:11:08,622][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:11:09,123][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:11:09,624][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:11:10,125][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:11:10,627][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:11:11,129][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:11:11,632][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:11:12,133][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:11:12,633][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:11:13,134][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:11:13,634][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:11:14,136][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:11:14,637][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:11:15,137][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:11:15,638][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:11:16,137][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:11:16,637][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:11:17,137][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:11:17,638][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:11:18,138][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:11:18,637][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:11:19,137][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:11:19,636][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:11:20,136][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:11:20,635][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:11:21,134][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:11:21,635][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:11:22,151][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:11:22,655][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:11:23,156][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:11:23,656][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:11:24,212][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:11:24,716][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:11:25,217][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:11:25,718][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:11:26,217][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:11:26,716][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:11:27,216][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:11:27,716][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:11:28,216][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:11:28,716][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:11:29,215][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:11:29,714][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:11:30,215][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:11:30,716][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:11:31,218][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:11:31,719][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:11:32,220][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:11:32,721][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:11:33,222][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:11:33,724][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:11:34,221][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:11:34,719][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:11:35,218][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:11:35,716][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:11:36,215][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:11:36,712][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:11:37,212][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:11:37,711][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:11:38,213][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:11:38,714][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:11:39,214][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:11:39,714][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:11:40,214][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:11:40,714][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:11:41,217][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:11:41,718][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:11:42,219][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:11:42,719][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:11:43,219][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:11:43,719][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:11:44,220][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:11:44,720][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:11:45,220][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:11:45,722][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:11:46,223][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:11:46,723][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:11:47,226][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:11:47,727][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:11:48,228][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:11:48,731][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:11:49,232][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:11:49,733][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:11:50,233][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:11:50,732][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:11:51,232][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:11:51,732][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:11:52,232][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:11:52,731][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:11:53,231][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:11:53,730][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:11:54,233][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:11:54,733][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:11:55,234][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:11:55,735][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:11:56,235][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:11:56,736][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:11:57,236][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:11:57,737][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:11:58,235][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:11:58,735][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:11:59,234][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:11:59,733][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:12:00,233][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:12:00,732][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:12:01,232][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:12:01,731][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:12:02,233][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:12:02,734][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:12:03,235][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:12:03,736][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:12:04,238][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:12:04,740][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:12:05,241][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:12:05,742][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-25 19:12:06,353][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:04 [2026-03-25 19:12:06,985][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:12:06,987][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:12:06,988][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:12:07,595][__main__][INFO] - Iteration 158 took 1m 14s (9.17% Gen, 90.01% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 15m 55s. Estimated total time: 61h 52m 50s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 45s, 500 more iterations: 10h 18m 48s. [2026-03-25 19:12:07,598][__main__][INFO] - Starting iteration 158. [2026-03-25 19:12:07,998][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:12:07,998][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:12:14,432][__main__][INFO] - Number of regex retries in iteration 158: 0 [2026-03-25 19:12:14,432][__main__][INFO] - agents played in iteration 158 are Bob, Alice [2026-03-25 19:12:15,352][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:12:15,929][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:12:16,386][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:12:16,890][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:12:17,391][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:12:17,891][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:12:18,391][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:12:18,891][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:12:19,391][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:12:19,891][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:12:20,391][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:12:20,892][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:12:21,393][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:12:21,894][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:12:22,395][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:12:22,896][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:12:23,396][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:12:23,896][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:12:24,398][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:12:24,900][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:12:25,401][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:12:25,902][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:12:26,403][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:12:26,904][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:12:27,405][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:12:27,907][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:12:28,408][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:12:28,908][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:12:29,409][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:12:29,909][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:12:30,410][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:12:30,910][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:12:31,412][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:12:31,913][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:12:32,413][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:12:32,913][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:12:33,413][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:12:33,913][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:12:34,412][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:12:34,912][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:12:35,410][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:12:35,910][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:12:36,408][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:12:36,906][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:12:37,404][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:12:37,902][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:12:38,400][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:12:38,898][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:12:39,396][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:12:39,895][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:12:40,397][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:12:40,898][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:12:41,401][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:12:41,903][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:12:42,406][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:12:42,907][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:12:43,408][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:12:43,910][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:12:44,411][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:12:44,912][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:12:45,414][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:12:45,915][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:12:46,415][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:12:46,915][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:12:47,415][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:12:47,916][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:12:48,417][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:12:48,919][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:12:49,421][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:12:49,922][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:12:50,422][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:12:50,922][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:12:51,424][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:12:51,925][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:12:52,426][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:12:52,927][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:12:53,427][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:12:53,928][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:12:54,429][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:12:54,930][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:12:55,430][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:12:55,932][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:12:56,432][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:12:56,933][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:12:57,434][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:12:57,936][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:12:58,436][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:12:58,938][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:12:59,439][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:12:59,940][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:13:00,439][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:13:00,938][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:13:01,438][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:13:01,937][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:13:02,437][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:13:02,936][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:13:03,436][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:13:03,936][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:13:04,435][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:13:04,934][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:13:05,434][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:13:05,934][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:13:06,434][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:13:06,934][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:13:07,435][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:13:07,935][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:13:08,433][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:13:08,933][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:13:09,431][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:13:09,930][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:13:10,429][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:13:10,927][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:13:11,427][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:13:11,925][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:13:12,427][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:13:12,928][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:13:13,429][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:13:13,930][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:13:14,431][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:13:14,932][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:13:15,433][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:13:15,934][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:13:16,435][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:13:16,935][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:13:17,435][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:13:17,936][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:13:18,436][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:13:18,936][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:13:19,436][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:13:19,937][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21722 tokens. [2026-03-25 19:13:20,545][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 19:13:21,269][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:13:21,271][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:13:21,272][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:13:21,881][__main__][INFO] - Iteration 159 took 1m 13s (8.71% Gen, 90.47% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 56m 2s. Estimated total time: 61h 34m 11s. Time estimates for 10 more iterations: 12m 18s, 100 more iterations: 2h 3m 8s, 500 more iterations: 10h 15m 41s. [2026-03-25 19:13:21,884][__main__][INFO] - Starting iteration 159. [2026-03-25 19:13:22,283][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:13:22,283][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:13:22,877][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:13:22,882][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:13:28,215][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:13:29,246][__main__][INFO] - Number of regex retries in iteration 159: 3 [2026-03-25 19:13:29,246][__main__][INFO] - agents played in iteration 159 are Bob, Alice [2026-03-25 19:13:30,167][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:13:30,743][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:13:31,199][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:13:31,704][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:13:32,204][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:13:32,704][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:13:33,204][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:13:33,707][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:13:34,207][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:13:34,708][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:13:35,211][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:13:35,713][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:13:36,214][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:13:36,715][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:13:37,216][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:13:37,718][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:13:38,219][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:13:38,720][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:13:39,219][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:13:39,718][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:13:40,217][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:13:40,717][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:13:41,218][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:13:41,719][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:13:42,219][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:13:42,718][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:13:43,217][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:13:43,716][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:13:44,215][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:13:44,715][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:13:45,214][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:13:45,713][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:13:46,212][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:13:46,712][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:13:47,213][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:13:47,715][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:13:48,217][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:13:48,719][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:13:49,221][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:13:49,724][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:13:50,228][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:13:50,729][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:13:51,231][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:13:51,732][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:13:52,234][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:13:52,735][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:13:53,237][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:13:53,738][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:13:54,240][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:13:54,741][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:13:55,243][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:13:55,745][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:13:56,247][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:13:56,748][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:13:57,250][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:13:57,752][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:13:58,253][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:13:58,755][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:13:59,255][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:13:59,755][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:14:00,256][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:14:00,756][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:14:01,258][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:14:01,759][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:14:02,259][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:14:02,760][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:14:03,260][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:14:03,760][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:14:04,258][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:14:04,760][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:14:05,260][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:14:05,760][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:14:06,259][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:14:06,759][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:14:07,260][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:14:07,761][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:14:08,262][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:14:08,765][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:14:09,267][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:14:09,768][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:14:10,270][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:14:10,771][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:14:11,272][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:14:11,772][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:14:12,271][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:14:12,770][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:14:13,270][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:14:13,770][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:14:14,269][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:14:14,769][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:14:15,267][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:14:15,767][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:14:16,267][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:14:16,766][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:14:17,265][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:14:17,765][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:14:18,264][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:14:18,763][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:14:19,263][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:14:19,766][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:14:20,268][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:14:20,769][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:14:21,270][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:14:21,771][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:14:22,271][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:14:22,772][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:14:23,274][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:14:23,775][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:14:24,277][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:14:24,779][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:14:25,281][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:14:25,787][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:14:26,289][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:14:26,792][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:14:27,295][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:14:27,797][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:14:28,299][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:14:28,801][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:14:29,306][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:14:29,808][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:14:30,310][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:14:30,812][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:14:31,313][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:14:31,814][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:14:32,315][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:14:32,816][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:14:33,317][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:14:33,817][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:14:34,318][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:14:34,818][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21715 tokens. [2026-03-25 19:14:35,426][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 19:14:36,147][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:14:36,149][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:14:36,151][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:14:36,853][__main__][INFO] - Iteration 160 took 1m 14s (9.34% Gen, 89.72% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 29m 8s. Estimated total time: 62h 8m 31s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 17s, 500 more iterations: 10h 21m 25s. [2026-03-25 19:14:36,855][__main__][INFO] - Starting iteration 160. [2026-03-25 19:14:37,257][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:14:37,257][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:14:43,874][__main__][INFO] - Number of regex retries in iteration 160: 0 [2026-03-25 19:14:43,875][__main__][INFO] - agents played in iteration 160 are Bob, Alice [2026-03-25 19:14:44,808][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:14:45,384][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:14:45,840][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:14:46,343][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:14:46,843][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:14:47,343][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:14:47,840][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:14:48,341][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:14:48,841][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:14:49,340][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:14:49,843][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:14:50,344][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:14:50,845][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:14:51,347][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:14:51,849][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:14:52,349][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:14:52,850][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:14:53,351][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:14:53,854][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:14:54,355][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:14:54,856][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:14:55,357][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:14:55,858][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:14:56,359][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:14:56,860][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:14:57,360][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:14:57,861][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:14:58,362][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:14:58,862][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:14:59,363][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:14:59,863][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:15:00,365][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:15:00,866][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:15:01,367][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:15:01,868][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:15:02,369][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:15:02,869][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:15:03,370][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:15:03,871][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:15:04,372][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:15:04,872][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:15:05,373][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:15:05,897][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:15:06,401][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:15:06,906][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:15:07,410][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:15:07,913][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:15:08,417][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:15:08,921][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:15:09,425][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:15:09,925][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:15:10,426][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:15:10,927][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:15:11,430][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:15:11,931][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:15:12,432][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:15:12,933][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:15:13,431][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:15:13,931][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:15:14,431][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:15:14,931][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:15:15,431][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:15:15,931][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:15:16,431][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:15:16,931][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:15:17,432][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:15:17,931][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:15:18,431][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:15:18,931][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:15:19,431][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:15:19,931][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:15:20,430][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:15:20,929][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:15:21,428][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:15:21,929][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:15:22,431][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:15:22,931][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:15:23,432][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:15:23,934][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:15:24,434][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:15:24,935][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:15:25,435][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:15:25,937][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:15:26,438][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:15:26,938][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:15:27,439][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:15:27,940][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:15:28,441][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:15:28,942][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:15:29,444][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:15:29,945][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:15:30,447][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:15:30,947][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:15:31,448][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:15:31,949][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:15:32,450][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:15:32,951][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:15:33,451][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:15:33,952][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:15:34,453][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:15:34,953][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:15:35,455][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:15:35,955][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:15:36,459][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:15:36,960][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:15:37,460][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:15:37,965][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:15:38,469][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:15:38,973][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:15:39,476][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:15:39,978][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:15:40,481][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:15:40,985][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:15:41,491][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:15:41,992][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:15:42,493][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:15:42,994][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:15:43,494][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:15:43,996][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:15:44,496][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:15:44,996][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:15:45,496][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:15:45,996][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:15:46,495][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:15:46,995][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:15:47,495][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:15:47,994][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:15:48,494][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:15:48,994][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:15:49,493][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21715 tokens. [2026-03-25 19:15:50,123][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.56%, ΔTime: 00:01:04 [2026-03-25 19:15:50,853][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:15:50,855][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:15:50,856][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:15:51,467][__main__][INFO] - Iteration 161 took 1m 14s (8.92% Gen, 90.26% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 9m 54s. Estimated total time: 61h 50m 33s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 41s, 500 more iterations: 10h 18m 25s. [2026-03-25 19:15:51,469][__main__][INFO] - Starting iteration 161. [2026-03-25 19:15:51,870][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:15:51,871][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:15:52,928][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:15:58,309][__main__][INFO] - Number of regex retries in iteration 161: 1 [2026-03-25 19:15:58,310][__main__][INFO] - agents played in iteration 161 are Bob, Alice [2026-03-25 19:15:59,252][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:15:59,839][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:16:00,299][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:16:00,807][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:16:01,310][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:16:01,814][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:16:02,317][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:16:02,820][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:16:03,323][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:16:03,827][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:16:04,329][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:16:04,829][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:16:05,330][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:16:05,832][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:16:06,333][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:16:06,834][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:16:07,336][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:16:07,838][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:16:08,339][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:16:08,841][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:16:09,341][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:16:09,843][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:16:10,345][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:16:10,846][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:16:11,350][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:16:11,852][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:16:12,354][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:16:12,856][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:16:13,357][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:16:13,858][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:16:14,359][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:16:14,861][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:16:15,363][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:16:15,866][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:16:16,367][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:16:16,868][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:16:17,369][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:16:17,870][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:16:18,372][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:16:18,873][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:16:19,374][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:16:19,874][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:16:20,375][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:16:20,875][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:16:21,376][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:16:21,876][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:16:22,376][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:16:22,875][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:16:23,375][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:16:23,875][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:16:24,376][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:16:24,877][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:16:25,377][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:16:25,878][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:16:26,378][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:16:26,880][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:16:27,381][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:16:27,883][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:16:28,386][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:16:28,888][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:16:29,391][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:16:29,894][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:16:30,396][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:16:30,899][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:16:31,401][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:16:31,903][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:16:32,407][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:16:32,909][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:16:33,413][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:16:33,916][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:16:34,418][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:16:34,921][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:16:35,425][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:16:35,927][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:16:36,429][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:16:36,931][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:16:37,432][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:16:37,933][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:16:38,434][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:16:38,935][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:16:39,436][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:16:39,938][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:16:40,439][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:16:40,939][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:16:41,443][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:16:41,945][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:16:42,447][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:16:42,948][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:16:43,449][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:16:43,950][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:16:44,452][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:16:44,954][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:16:45,455][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:16:45,957][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:16:46,458][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:16:46,959][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:16:47,461][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:16:47,964][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:16:48,466][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:16:48,968][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:16:49,469][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:16:49,970][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:16:50,472][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:16:50,973][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:16:51,475][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:16:51,977][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:16:52,478][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:16:52,979][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:16:53,483][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:16:53,985][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:16:54,487][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:16:54,987][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:16:55,488][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:16:55,989][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:16:56,491][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:16:56,993][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:16:57,494][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:16:57,995][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:16:58,496][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:16:58,996][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:16:59,497][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:16:59,998][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:17:00,500][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:17:01,003][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:17:01,506][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:17:02,010][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:17:02,512][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:17:03,016][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:17:03,519][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:17:04,021][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21708 tokens. [2026-03-25 19:17:04,638][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 19:17:05,375][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:17:05,377][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:17:05,379][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:17:06,011][__main__][INFO] - Iteration 162 took 1m 14s (8.68% Gen, 90.46% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 58h 5m 12s. Estimated total time: 61h 47m 4s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 34s, 500 more iterations: 10h 17m 50s. [2026-03-25 19:17:06,013][__main__][INFO] - Starting iteration 162. [2026-03-25 19:17:06,414][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:17:06,415][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:17:08,010][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:17:12,795][__main__][INFO] - Number of regex retries in iteration 162: 1 [2026-03-25 19:17:12,795][__main__][INFO] - agents played in iteration 162 are Bob, Alice [2026-03-25 19:17:13,729][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:17:14,310][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:17:14,769][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:17:15,277][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:17:15,780][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:17:16,284][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:17:16,787][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:17:17,291][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:17:17,794][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:17:18,297][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:17:18,797][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:17:19,297][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:17:19,797][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:17:20,297][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:17:20,797][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:17:21,297][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:17:21,796][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:17:22,297][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:17:22,798][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:17:23,299][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:17:23,800][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:17:24,301][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:17:24,802][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:17:25,302][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:17:25,803][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:17:26,304][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:17:26,805][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:17:27,306][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:17:27,807][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:17:28,307][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:17:28,808][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:17:29,309][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:17:29,810][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:17:30,311][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:17:30,812][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:17:31,312][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:17:31,812][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:17:32,312][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:17:32,812][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:17:33,312][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:17:33,812][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:17:34,312][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:17:34,813][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:17:35,314][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:17:35,815][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:17:36,315][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:17:36,817][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:17:37,320][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:17:37,822][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:17:38,322][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:17:38,823][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:17:39,324][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:17:39,827][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:17:40,328][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:17:40,830][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:17:41,334][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:17:41,836][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:17:42,337][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:17:42,837][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:17:43,336][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:17:43,838][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:17:44,338][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:17:44,838][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:17:45,337][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:17:45,838][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:17:46,338][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:17:46,841][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:17:47,345][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:17:47,848][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:17:48,351][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:17:48,855][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:17:49,358][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:17:49,861][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:17:50,364][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:17:50,865][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:17:51,365][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:17:51,867][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:17:52,368][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:17:52,869][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:17:53,370][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:17:53,871][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:17:54,372][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:17:54,873][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:17:55,374][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:17:55,875][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:17:56,376][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:17:56,876][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:17:57,376][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:17:57,877][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:17:58,377][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:17:58,877][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:17:59,378][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:17:59,877][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:18:00,377][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:18:00,877][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:18:01,376][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:18:01,876][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:18:02,376][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:18:02,877][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:18:03,376][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:18:03,875][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:18:04,375][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:18:04,874][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:18:05,374][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:18:05,874][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:18:06,376][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:18:06,887][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:18:07,390][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:18:07,894][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:18:08,395][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:18:08,898][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:18:09,399][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:18:09,910][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:18:10,413][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:18:10,916][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:18:11,421][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:18:11,924][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:18:12,425][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:18:12,927][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:18:13,431][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:18:13,944][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:18:14,446][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:18:14,949][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:18:15,452][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:18:15,953][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:18:16,455][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:18:16,956][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:18:17,457][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:18:17,957][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:18:18,469][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21743 tokens. [2026-03-25 19:18:19,110][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:04 [2026-03-25 19:18:19,838][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:18:19,840][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:18:19,841][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:18:20,524][__main__][INFO] - Iteration 163 took 1m 14s (8.61% Gen, 90.47% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 58h 2m 22s. Estimated total time: 61h 45m 29s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 30s, 500 more iterations: 10h 17m 34s. [2026-03-25 19:18:20,526][__main__][INFO] - Starting iteration 163. [2026-03-25 19:18:20,924][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:18:20,925][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:18:22,560][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:18:24,807][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:18:27,430][__main__][INFO] - Number of regex retries in iteration 163: 2 [2026-03-25 19:18:27,430][__main__][INFO] - agents played in iteration 163 are Bob, Alice [2026-03-25 19:18:28,362][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:18:28,950][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:18:29,412][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:18:29,919][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:18:30,421][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:18:30,924][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:18:31,426][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:18:31,927][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:18:32,429][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:18:32,931][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:18:33,432][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:18:33,935][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:18:34,444][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:18:34,947][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:18:35,449][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:18:35,952][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:18:36,454][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:18:36,955][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:18:37,457][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:18:37,957][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:18:38,458][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:18:38,958][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:18:39,458][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:18:39,959][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:18:40,460][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:18:40,961][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:18:41,464][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:18:41,964][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:18:42,465][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:18:42,967][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:18:43,469][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:18:43,981][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:18:44,483][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:18:44,985][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:18:45,488][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:18:45,991][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:18:46,493][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:18:46,995][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:18:47,496][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:18:47,996][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:18:48,497][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:18:48,997][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:18:49,499][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:18:49,999][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:18:50,500][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:18:51,001][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:18:51,502][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:18:52,005][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:18:52,507][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:18:53,010][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:18:53,514][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:18:54,023][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:18:54,529][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:18:55,033][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:18:55,536][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:18:56,038][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:18:56,541][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:18:57,044][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:18:57,547][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:18:58,048][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:18:58,549][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:18:59,050][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:18:59,552][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:19:00,053][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:19:00,554][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:19:01,055][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:19:01,555][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:19:02,056][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:19:02,556][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:19:03,057][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:19:03,558][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:19:04,058][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:19:04,558][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:19:05,059][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:19:05,559][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:19:06,059][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:19:06,560][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:19:07,063][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:19:07,565][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:19:08,066][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:19:08,566][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:19:09,067][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:19:09,568][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:19:10,068][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:19:10,568][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:19:11,069][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:19:11,572][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:19:12,072][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:19:12,573][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:19:13,073][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:19:13,574][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:19:14,074][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:19:14,575][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:19:15,074][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:19:15,574][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:19:16,074][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:19:16,574][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:19:17,075][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:19:17,575][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:19:18,075][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:19:18,575][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:19:19,074][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:19:19,574][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:19:20,074][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:19:20,574][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:19:21,075][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:19:21,575][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:19:22,075][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:19:22,574][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:19:23,075][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:19:23,575][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:19:24,075][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:19:24,576][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:19:25,076][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:19:25,580][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:19:26,083][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:19:26,596][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:19:27,099][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:19:27,602][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:19:28,106][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:19:28,610][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:19:29,113][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:19:29,615][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:19:30,116][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:19:30,618][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:19:31,120][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:19:31,621][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:19:32,122][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:19:32,623][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:19:33,124][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 19:19:33,768][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 19:19:34,493][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:19:34,495][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:19:34,497][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:19:35,194][__main__][INFO] - Iteration 164 took 1m 14s (8.76% Gen, 90.30% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 58h 9m 11s. Estimated total time: 61h 53m 33s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 47s, 500 more iterations: 10h 18m 55s. [2026-03-25 19:19:35,196][__main__][INFO] - Starting iteration 164. [2026-03-25 19:19:35,599][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:19:35,600][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:19:37,482][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:19:42,234][__main__][INFO] - Number of regex retries in iteration 164: 1 [2026-03-25 19:19:42,235][__main__][INFO] - agents played in iteration 164 are Bob, Alice [2026-03-25 19:19:43,181][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:19:44,042][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:19:44,501][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:19:45,008][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:19:45,510][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:19:46,010][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:19:46,512][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:19:47,013][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:19:47,516][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:19:48,017][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:19:48,521][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:19:49,022][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:19:49,522][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:19:50,025][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:19:50,527][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:19:51,028][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:19:51,529][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:19:52,030][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:19:52,533][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:19:53,034][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:19:53,536][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:19:54,038][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:19:54,539][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:19:55,041][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:19:55,542][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:19:56,047][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:19:56,548][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:19:57,048][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:19:57,548][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:19:58,048][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:19:58,548][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:19:59,048][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:19:59,549][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:20:00,049][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:20:00,549][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:20:01,050][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:20:01,550][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:20:02,051][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:20:02,552][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:20:03,053][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:20:03,553][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:20:04,054][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:20:04,555][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:20:05,056][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:20:05,557][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:20:06,058][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:20:06,567][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:20:07,069][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:20:07,571][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:20:08,072][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:20:08,593][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:20:09,099][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:20:09,601][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:20:10,103][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:20:10,606][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:20:11,108][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:20:11,614][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:20:12,116][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:20:12,617][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:20:13,118][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:20:13,619][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:20:14,120][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:20:14,621][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:20:15,122][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:20:15,622][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:20:16,123][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:20:16,623][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:20:17,124][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:20:17,625][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:20:18,126][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:20:18,626][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:20:19,127][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:20:19,627][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:20:20,128][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:20:20,630][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:20:21,131][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:20:21,632][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:20:22,133][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:20:22,633][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:20:23,134][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:20:23,634][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:20:24,134][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:20:24,636][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:20:25,139][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:20:25,640][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:20:26,140][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:20:26,652][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:20:27,155][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:20:27,657][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:20:28,159][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:20:28,660][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:20:29,161][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:20:29,663][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:20:30,164][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:20:30,665][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:20:31,165][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:20:31,666][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:20:32,169][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:20:32,669][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:20:33,172][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:20:33,672][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:20:34,172][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:20:34,673][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:20:35,174][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:20:35,675][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:20:36,176][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:20:36,676][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:20:37,179][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:20:37,680][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:20:38,182][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:20:38,686][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:20:39,187][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:20:39,689][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:20:40,190][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:20:40,691][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:20:41,194][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:20:41,696][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:20:42,198][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:20:42,698][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:20:43,199][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:20:43,700][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:20:44,203][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:20:44,706][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:20:45,207][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:20:45,709][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:20:46,211][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:20:46,712][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:20:47,215][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:20:47,717][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:20:48,219][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21748 tokens. [2026-03-25 19:20:48,860][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-25 19:20:49,582][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:20:49,584][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:20:49,586][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:20:50,283][__main__][INFO] - Iteration 165 took 1m 14s (8.88% Gen, 90.18% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 58h 28m 37s. Estimated total time: 62h 14m 14s. Time estimates for 10 more iterations: 12m 26s, 100 more iterations: 2h 4m 28s, 500 more iterations: 10h 22m 22s. [2026-03-25 19:20:50,285][__main__][INFO] - Starting iteration 165. [2026-03-25 19:20:50,683][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:20:50,684][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:20:51,284][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:20:56,980][__main__][INFO] - Number of regex retries in iteration 165: 1 [2026-03-25 19:20:56,981][__main__][INFO] - agents played in iteration 165 are Bob, Alice [2026-03-25 19:20:57,919][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:20:58,764][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:20:59,220][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:20:59,726][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:21:00,227][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:21:00,728][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:21:01,229][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:21:01,729][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:21:02,230][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:21:02,730][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:21:03,232][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:21:03,732][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:21:04,232][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:21:04,733][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:21:05,234][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:21:05,734][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:21:06,236][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:21:06,736][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:21:07,239][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:21:07,741][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:21:08,244][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:21:08,745][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:21:09,247][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:21:09,749][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:21:10,251][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:21:10,753][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:21:11,255][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:21:11,758][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:21:12,258][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:21:12,758][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:21:13,259][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:21:13,761][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:21:14,261][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:21:14,776][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:21:15,278][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:21:15,780][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:21:16,281][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:21:16,785][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:21:17,286][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:21:17,787][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:21:18,288][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:21:18,790][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:21:19,292][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:21:19,793][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:21:20,294][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:21:20,795][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:21:21,295][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:21:21,795][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:21:22,296][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:21:22,798][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:21:23,299][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:21:23,801][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:21:24,303][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:21:24,808][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:21:25,309][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:21:25,812][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:21:26,314][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:21:26,815][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:21:27,315][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:21:27,814][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:21:28,314][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:21:28,815][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:21:29,314][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:21:29,813][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:21:30,312][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:21:30,812][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:21:31,312][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:21:31,811][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:21:32,312][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:21:32,812][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:21:33,313][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:21:33,813][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:21:34,313][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:21:34,814][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:21:35,314][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:21:35,815][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:21:36,315][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:21:36,815][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:21:37,314][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:21:37,814][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:21:38,314][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:21:38,814][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:21:39,316][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:21:39,818][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:21:40,320][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:21:40,822][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:21:41,328][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:21:41,832][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:21:42,335][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:21:42,837][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:21:43,337][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:21:43,838][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:21:44,350][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:21:44,852][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:21:45,353][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:21:45,855][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:21:46,356][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:21:46,858][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:21:47,358][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:21:47,860][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:21:48,360][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:21:48,862][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:21:49,362][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:21:49,863][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:21:50,365][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:21:50,867][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:21:51,367][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:21:51,868][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:21:52,369][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:21:52,870][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:21:53,371][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:21:53,872][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:21:54,373][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:21:54,873][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:21:55,374][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:21:55,876][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:21:56,377][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:21:56,880][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:21:57,381][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:21:57,883][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:21:58,388][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:21:58,890][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:21:59,391][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:21:59,891][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:22:00,392][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:22:00,891][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:22:01,391][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:22:01,890][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:22:02,390][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:22:02,891][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21739 tokens. [2026-03-25 19:22:03,527][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 19:22:04,253][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:22:04,255][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:22:04,256][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:22:04,954][__main__][INFO] - Iteration 166 took 1m 14s (8.48% Gen, 90.58% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 58h 6m 43s. Estimated total time: 61h 53m 34s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 47s, 500 more iterations: 10h 18m 55s. [2026-03-25 19:22:04,956][__main__][INFO] - Starting iteration 166. [2026-03-25 19:22:05,357][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:22:05,357][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:22:10,167][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:22:12,434][__main__][INFO] - Number of regex retries in iteration 166: 1 [2026-03-25 19:22:12,435][__main__][INFO] - agents played in iteration 166 are Bob, Alice [2026-03-25 19:22:13,368][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:22:13,947][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:22:14,404][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:22:14,910][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:22:15,410][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:22:15,910][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:22:16,411][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:22:16,912][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:22:17,412][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:22:17,913][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:22:18,412][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:22:18,913][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:22:19,414][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:22:19,915][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:22:20,414][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:22:20,914][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:22:21,415][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:22:21,914][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:22:22,417][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:22:22,919][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:22:23,420][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:22:23,922][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:22:24,423][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:22:24,925][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:22:25,428][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:22:25,929][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:22:26,430][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:22:26,931][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:22:27,432][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:22:27,933][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:22:28,434][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:22:28,935][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:22:29,436][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:22:29,937][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:22:30,438][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:22:30,939][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:22:31,441][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:22:31,942][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:22:32,445][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:22:32,947][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:22:33,448][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:22:33,949][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:22:34,451][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:22:34,952][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:22:35,453][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:22:35,954][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:22:36,455][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:22:36,955][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:22:37,455][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:22:37,956][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:22:38,456][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:22:38,957][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:22:39,456][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:22:39,958][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:22:40,458][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:22:40,959][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:22:41,462][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:22:41,967][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:22:42,470][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:22:42,973][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:22:43,475][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:22:43,977][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:22:44,479][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:22:44,981][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:22:45,482][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:22:45,984][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:22:46,485][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:22:46,989][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:22:47,489][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:22:47,990][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:22:48,491][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:22:48,992][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:22:49,492][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:22:49,994][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:22:50,494][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:22:50,996][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:22:51,496][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:22:51,996][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:22:52,496][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:22:52,997][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:22:53,497][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:22:53,998][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:22:54,500][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:22:55,001][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:22:55,502][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:22:56,004][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:22:56,508][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:22:57,010][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:22:57,511][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:22:58,014][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:22:58,516][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:22:59,016][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:22:59,518][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:23:00,020][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:23:00,521][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:23:01,023][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:23:01,523][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:23:02,023][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:23:02,526][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:23:03,028][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:23:03,530][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:23:04,032][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:23:04,533][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:23:05,034][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:23:05,535][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:23:06,037][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:23:06,538][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:23:07,039][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:23:07,540][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:23:08,041][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:23:08,541][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:23:09,043][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:23:09,544][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:23:10,046][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:23:10,547][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:23:11,048][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:23:11,550][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:23:12,051][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:23:12,551][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:23:13,052][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:23:13,552][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:23:14,052][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:23:14,552][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:23:15,053][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:23:15,555][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:23:16,056][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:23:16,557][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:23:17,058][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:23:17,558][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:23:18,058][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21742 tokens. [2026-03-25 19:23:18,671][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-25 19:23:19,401][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:23:19,404][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:23:19,405][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:23:20,114][__main__][INFO] - Iteration 167 took 1m 14s (9.47% Gen, 89.58% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 58h 29m 47s. Estimated total time: 62h 17m 54s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 35s, 500 more iterations: 10h 22m 59s. [2026-03-25 19:23:20,116][__main__][INFO] - Starting iteration 167. [2026-03-25 19:23:20,514][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:23:20,515][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:23:21,708][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:23:27,430][__main__][INFO] - Number of regex retries in iteration 167: 1 [2026-03-25 19:23:27,431][__main__][INFO] - agents played in iteration 167 are Bob, Alice [2026-03-25 19:23:28,431][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:23:29,010][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:23:29,467][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:23:29,971][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:23:30,472][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:23:30,973][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:23:31,473][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:23:31,973][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:23:32,473][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:23:32,974][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:23:33,476][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:23:33,977][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:23:34,477][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:23:34,978][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:23:35,477][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:23:35,977][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:23:36,478][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:23:36,979][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:23:37,481][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:23:37,980][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:23:38,479][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:23:38,979][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:23:39,479][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:23:39,977][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:23:40,477][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:23:40,977][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:23:41,478][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:23:41,978][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:23:42,476][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:23:42,974][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:23:43,473][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:23:43,973][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:23:44,472][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:23:44,973][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:23:45,472][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:23:45,971][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:23:46,469][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:23:46,968][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:23:47,468][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:23:47,968][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:23:48,468][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:23:48,967][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:23:49,469][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:23:49,969][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:23:50,469][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:23:50,970][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:23:51,470][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:23:51,970][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:23:52,470][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:23:52,971][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:23:53,470][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:23:53,972][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:23:54,472][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:23:54,973][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:23:55,473][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:23:55,974][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:23:56,474][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:23:56,974][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:23:57,474][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:23:57,972][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:23:58,472][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:23:58,971][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:23:59,471][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:23:59,972][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:24:00,471][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:24:00,971][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:24:01,471][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:24:01,971][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:24:02,471][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:24:02,972][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:24:03,472][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:24:03,971][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:24:04,472][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:24:04,972][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:24:05,473][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:24:05,973][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:24:06,474][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:24:06,974][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:24:07,474][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:24:07,975][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:24:08,475][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:24:08,976][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:24:09,474][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:24:09,974][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:24:10,473][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:24:10,972][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:24:11,474][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:24:11,974][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:24:12,474][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:24:12,973][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:24:13,472][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:24:13,972][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:24:14,471][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:24:14,972][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:24:15,473][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:24:15,974][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:24:16,473][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:24:16,973][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:24:17,473][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:24:17,972][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:24:18,471][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:24:18,972][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:24:19,471][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:24:19,970][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:24:20,469][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:24:20,968][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:24:21,468][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:24:21,968][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:24:22,469][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:24:22,969][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:24:23,469][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:24:23,975][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:24:24,475][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:24:24,976][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:24:25,477][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:24:25,978][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:24:26,479][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:24:26,980][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:24:27,481][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:24:27,984][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:24:28,486][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:24:28,987][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:24:29,487][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:24:29,986][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:24:30,487][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:24:30,988][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:24:31,487][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:24:31,988][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:24:32,488][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:24:32,987][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21749 tokens. [2026-03-25 19:24:33,599][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.23%, ΔTime: 00:01:04 [2026-03-25 19:24:34,331][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:24:34,333][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:24:34,334][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:24:35,079][__main__][INFO] - Iteration 168 took 1m 14s (9.27% Gen, 89.73% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 18m 52s. Estimated total time: 62h 8m 14s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 16s, 500 more iterations: 10h 21m 22s. [2026-03-25 19:24:35,081][__main__][INFO] - Starting iteration 168. [2026-03-25 19:24:35,480][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:24:35,480][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:24:41,805][__main__][INFO] - Number of regex retries in iteration 168: 0 [2026-03-25 19:24:41,806][__main__][INFO] - agents played in iteration 168 are Bob, Alice [2026-03-25 19:24:42,724][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:24:43,300][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:24:43,761][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:24:44,268][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:24:44,772][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:24:45,274][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:24:45,776][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:24:46,279][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:24:46,782][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:24:47,284][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:24:47,787][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:24:48,288][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:24:48,789][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:24:49,291][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:24:49,793][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:24:50,295][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:24:50,796][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:24:51,297][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:24:51,797][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:24:52,296][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:24:52,796][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:24:53,296][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:24:53,796][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:24:54,295][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:24:54,794][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:24:55,294][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:24:55,795][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:24:56,296][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:24:56,795][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:24:57,295][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:24:57,794][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:24:58,294][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:24:58,794][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:24:59,295][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:24:59,796][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:25:00,297][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:25:00,798][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:25:01,297][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:25:01,796][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:25:02,296][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:25:02,796][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:25:03,296][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:25:03,797][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:25:04,297][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:25:04,797][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:25:05,296][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:25:05,796][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:25:06,296][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:25:06,798][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:25:07,299][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:25:07,800][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:25:08,300][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:25:08,801][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:25:09,302][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:25:09,803][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:25:10,305][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:25:10,807][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:25:11,311][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:25:11,813][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:25:12,314][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:25:12,815][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:25:13,317][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:25:13,818][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:25:14,319][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:25:14,820][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:25:15,322][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:25:15,826][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:25:16,329][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:25:16,832][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:25:17,335][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:25:17,837][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:25:18,340][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:25:18,843][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:25:19,345][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:25:19,847][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:25:20,349][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:25:20,850][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:25:21,353][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:25:21,855][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:25:22,356][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:25:22,858][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:25:23,360][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:25:23,861][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:25:24,363][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:25:24,863][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:25:25,363][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:25:25,863][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:25:26,363][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:25:26,866][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:25:27,367][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:25:27,867][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:25:28,367][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:25:28,867][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:25:29,368][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:25:29,869][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:25:30,369][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:25:30,869][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:25:31,368][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:25:31,868][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:25:32,369][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:25:32,868][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:25:33,368][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:25:33,868][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:25:34,368][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:25:34,868][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:25:35,368][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:25:35,869][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:25:36,369][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:25:36,869][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:25:37,369][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:25:37,869][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:25:38,370][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:25:38,871][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:25:39,371][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:25:39,871][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:25:40,372][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:25:40,873][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:25:41,376][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:25:41,877][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:25:42,377][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:25:42,877][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:25:43,376][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:25:43,877][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:25:44,378][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:25:44,878][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:25:45,378][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:25:45,879][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:25:46,380][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:25:46,881][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:25:47,382][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 19:25:47,988][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.31%, Current % of VRAM taken: 60.66%, Block Peak % of device VRAM: 62.61%, ΔTime: 00:01:04 [2026-03-25 19:25:48,708][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:25:48,710][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:25:48,711][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:25:49,347][__main__][INFO] - Iteration 169 took 1m 13s (8.56% Gen, 90.57% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 42m 49s. Estimated total time: 61h 33m 25s. Time estimates for 10 more iterations: 12m 18s, 100 more iterations: 2h 3m 6s, 500 more iterations: 10h 15m 34s. [2026-03-25 19:25:49,349][__main__][INFO] - Starting iteration 169. [2026-03-25 19:25:49,750][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:25:49,751][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:25:50,348][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:25:56,209][__main__][INFO] - Number of regex retries in iteration 169: 1 [2026-03-25 19:25:56,210][__main__][INFO] - agents played in iteration 169 are Bob, Alice [2026-03-25 19:25:57,152][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:25:57,727][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:25:58,183][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:25:58,689][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:25:59,190][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:25:59,692][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:26:00,192][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:26:00,692][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:26:01,195][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:26:01,696][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:26:02,197][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:26:02,696][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:26:03,197][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:26:03,697][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:26:04,198][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:26:04,698][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:26:05,198][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:26:05,697][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:26:06,199][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:26:06,699][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:26:07,201][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:26:07,709][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:26:08,212][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:26:08,713][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:26:09,216][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:26:09,717][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:26:10,218][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:26:10,719][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:26:11,222][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:26:11,724][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:26:12,226][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:26:12,727][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:26:13,228][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:26:13,729][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:26:14,231][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:26:14,733][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:26:15,235][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:26:15,735][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:26:16,238][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:26:16,739][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:26:17,239][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:26:17,741][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:26:18,244][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:26:18,747][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:26:19,249][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:26:19,751][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:26:20,254][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:26:20,755][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:26:21,256][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:26:21,757][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:26:22,258][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:26:22,758][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:26:23,259][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:26:23,758][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:26:24,258][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:26:24,758][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:26:25,258][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:26:25,757][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:26:26,258][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:26:26,759][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:26:27,259][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:26:27,759][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:26:28,260][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:26:28,760][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:26:29,261][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:26:29,761][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:26:30,262][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:26:30,762][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:26:31,262][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:26:31,764][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:26:32,264][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:26:32,766][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:26:33,266][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:26:33,767][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:26:34,267][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:26:34,768][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:26:35,268][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:26:35,769][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:26:36,268][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:26:36,769][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:26:37,271][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:26:37,772][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:26:38,273][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:26:38,774][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:26:39,275][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:26:39,776][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:26:40,275][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:26:40,775][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:26:41,277][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:26:41,778][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:26:42,279][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:26:42,778][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:26:43,278][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:26:43,778][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:26:44,276][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:26:44,776][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:26:45,276][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:26:45,777][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:26:46,276][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:26:46,778][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:26:47,278][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:26:47,778][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:26:48,278][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:26:48,779][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:26:49,280][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:26:49,781][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:26:50,282][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:26:50,783][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:26:51,287][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:26:51,788][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:26:52,290][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:26:52,791][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:26:53,292][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:26:53,793][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:26:54,294][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:26:54,794][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:26:55,296][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:26:55,795][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:26:56,296][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:26:56,796][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:26:57,296][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:26:57,795][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:26:58,296][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:26:58,796][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:26:59,296][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:26:59,796][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:27:00,296][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:27:00,796][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:27:01,296][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:27:01,796][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 19:27:02,407][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 19:27:03,136][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:27:03,138][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:27:03,140][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:27:03,853][__main__][INFO] - Iteration 170 took 1m 14s (8.72% Gen, 90.32% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 53m 21s. Estimated total time: 61h 45m 11s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 30s, 500 more iterations: 10h 17m 31s. [2026-03-25 19:27:03,855][__main__][INFO] - Starting iteration 170. [2026-03-25 19:27:04,257][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:27:04,257][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:27:06,932][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:27:07,071][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:27:10,736][__main__][INFO] - Number of regex retries in iteration 170: 2 [2026-03-25 19:27:10,737][__main__][INFO] - agents played in iteration 170 are Bob, Alice [2026-03-25 19:27:11,651][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:27:12,230][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:27:12,688][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:27:13,193][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:27:13,694][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:27:14,195][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:27:14,695][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:27:15,196][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:27:15,697][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:27:16,196][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:27:16,696][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:27:17,196][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:27:17,696][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:27:18,197][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:27:18,697][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:27:19,197][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:27:19,696][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:27:20,197][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:27:20,696][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:27:21,196][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:27:21,695][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:27:22,195][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:27:22,694][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:27:23,194][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:27:23,694][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:27:24,195][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:27:24,700][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:27:25,201][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:27:25,702][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:27:26,203][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:27:26,707][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:27:27,209][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:27:27,710][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:27:28,212][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:27:28,713][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:27:29,214][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:27:29,716][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:27:30,219][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:27:30,722][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:27:31,224][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:27:31,725][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:27:32,227][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:27:32,728][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:27:33,229][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:27:33,729][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:27:34,230][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:27:34,730][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:27:35,231][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:27:35,731][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:27:36,232][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:27:36,733][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:27:37,233][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:27:37,733][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:27:38,233][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:27:38,733][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:27:39,233][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:27:39,733][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:27:40,233][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:27:40,733][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:27:41,236][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:27:41,736][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:27:42,236][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:27:42,736][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:27:43,236][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:27:43,736][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:27:44,236][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:27:44,736][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:27:45,236][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:27:45,737][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:27:46,237][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:27:46,737][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:27:47,238][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:27:47,739][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:27:48,239][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:27:48,739][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:27:49,239][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:27:49,739][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:27:50,239][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:27:50,740][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:27:51,240][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:27:51,741][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:27:52,240][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:27:52,740][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:27:53,242][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:27:53,743][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:27:54,243][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:27:54,742][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:27:55,243][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:27:55,743][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:27:56,244][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:27:56,746][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:27:57,247][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:27:57,748][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:27:58,248][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:27:58,750][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:27:59,251][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:27:59,752][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:28:00,253][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:28:00,754][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:28:01,254][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:28:01,754][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:28:02,254][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:28:02,755][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:28:03,256][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:28:03,756][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:28:04,256][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:28:04,757][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:28:05,257][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:28:05,758][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:28:06,258][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:28:06,757][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:28:07,258][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:28:07,757][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:28:08,257][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:28:08,757][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:28:09,256][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:28:09,755][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:28:10,255][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:28:10,755][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:28:11,256][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:28:11,755][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:28:12,256][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:28:12,756][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:28:13,257][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:28:13,757][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:28:14,257][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:28:14,757][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:28:15,257][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:28:15,757][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:28:16,256][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 19:28:16,868][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 19:28:17,595][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:28:17,597][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:28:17,598][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:28:18,296][__main__][INFO] - Iteration 171 took 1m 14s (8.75% Gen, 90.30% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 48m 55s. Estimated total time: 61h 42m 0s. Time estimates for 10 more iterations: 12m 20s, 100 more iterations: 2h 3m 24s, 500 more iterations: 10h 17m 0s. [2026-03-25 19:28:18,298][__main__][INFO] - Starting iteration 171. [2026-03-25 19:28:18,699][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:28:18,700][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:28:24,988][__main__][INFO] - Number of regex retries in iteration 171: 0 [2026-03-25 19:28:24,990][__main__][INFO] - agents played in iteration 171 are Bob, Alice [2026-03-25 19:28:25,917][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:28:26,494][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:28:26,951][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:28:27,457][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:28:27,958][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:28:28,461][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:28:28,963][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:28:29,464][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:28:29,966][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:28:30,469][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:28:30,970][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:28:31,471][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:28:31,971][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:28:32,472][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:28:32,972][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:28:33,474][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:28:33,975][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:28:34,475][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:28:34,976][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:28:35,477][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:28:35,978][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:28:36,479][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:28:36,979][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:28:37,479][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:28:37,980][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:28:38,481][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:28:38,980][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:28:39,480][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:28:39,979][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:28:40,478][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:28:40,978][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:28:41,479][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:28:41,979][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:28:42,479][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:28:42,979][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:28:43,479][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:28:43,978][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:28:44,478][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:28:44,978][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:28:45,478][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:28:45,978][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:28:46,478][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:28:46,978][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:28:47,477][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:28:47,977][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:28:48,477][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:28:48,978][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:28:49,478][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:28:49,978][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:28:50,478][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:28:50,978][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:28:51,477][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:28:51,978][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:28:52,478][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:28:52,978][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:28:53,478][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:28:53,977][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:28:54,477][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:28:54,977][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:28:55,477][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:28:55,978][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:28:56,478][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:28:56,978][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:28:57,478][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:28:57,978][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:28:58,478][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:28:58,979][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:28:59,481][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:28:59,981][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:29:00,483][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:29:00,985][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:29:01,488][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:29:01,989][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:29:02,491][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:29:02,992][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:29:03,492][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:29:03,993][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:29:04,494][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:29:04,995][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:29:05,497][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:29:05,998][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:29:06,499][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:29:06,999][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:29:07,502][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:29:08,006][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:29:08,508][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:29:09,009][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:29:09,511][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:29:10,012][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:29:10,513][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:29:11,013][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:29:11,517][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:29:12,018][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:29:12,518][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:29:13,018][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:29:13,531][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:29:14,033][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:29:14,534][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:29:15,036][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:29:15,537][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:29:16,038][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:29:16,539][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:29:17,041][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:29:17,542][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:29:18,043][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:29:18,545][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:29:19,045][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:29:19,547][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:29:20,049][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:29:20,549][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:29:21,050][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:29:21,549][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:29:22,050][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:29:22,550][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:29:23,051][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:29:23,551][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:29:24,052][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:29:24,552][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:29:25,052][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:29:25,552][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:29:26,053][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:29:26,554][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:29:27,055][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:29:27,555][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:29:28,056][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:29:28,556][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:29:29,057][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:29:29,558][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:29:30,058][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:29:30,558][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 19:29:31,165][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 19:29:31,891][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:29:31,893][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:29:31,894][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:29:32,598][__main__][INFO] - Iteration 172 took 1m 13s (8.51% Gen, 90.54% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 40m 37s. Estimated total time: 61h 34m 57s. Time estimates for 10 more iterations: 12m 18s, 100 more iterations: 2h 3m 9s, 500 more iterations: 10h 15m 49s. [2026-03-25 19:29:32,601][__main__][INFO] - Starting iteration 172. [2026-03-25 19:29:33,000][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:29:33,001][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:29:39,213][__main__][INFO] - Number of regex retries in iteration 172: 0 [2026-03-25 19:29:39,214][__main__][INFO] - agents played in iteration 172 are Bob, Alice [2026-03-25 19:29:40,138][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:29:40,710][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:29:41,169][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:29:41,676][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:29:42,178][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:29:42,679][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:29:43,181][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:29:43,682][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:29:44,185][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:29:44,687][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:29:45,188][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:29:45,687][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:29:46,188][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:29:46,689][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:29:47,189][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:29:47,689][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:29:48,189][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:29:48,690][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:29:49,193][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:29:49,695][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:29:50,197][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:29:50,700][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:29:51,202][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:29:51,705][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:29:52,206][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:29:52,709][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:29:53,209][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:29:53,710][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:29:54,210][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:29:54,711][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:29:55,211][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:29:55,712][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:29:56,212][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:29:56,713][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:29:57,215][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:29:57,716][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:29:58,217][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:29:58,718][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:29:59,218][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:29:59,719][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:30:00,221][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:30:00,721][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:30:01,223][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:30:01,724][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:30:02,224][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:30:02,725][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:30:03,228][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:30:03,728][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:30:04,229][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:30:04,730][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:30:05,232][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:30:05,732][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:30:06,232][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:30:06,734][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:30:07,236][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:30:07,736][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:30:08,236][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:30:08,736][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:30:09,237][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:30:09,738][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:30:10,240][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:30:10,741][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:30:11,244][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:30:11,748][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:30:12,250][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:30:12,753][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:30:13,256][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:30:13,757][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:30:14,259][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:30:14,760][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:30:15,261][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:30:15,763][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:30:16,265][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:30:16,767][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:30:17,267][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:30:17,767][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:30:18,268][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:30:18,769][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:30:19,269][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:30:19,769][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:30:20,269][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:30:20,769][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:30:21,270][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:30:21,772][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:30:22,274][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:30:22,776][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:30:23,277][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:30:23,778][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:30:24,279][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:30:24,781][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:30:25,283][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:30:25,784][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:30:26,285][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:30:26,786][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:30:27,287][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:30:27,788][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:30:28,288][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:30:28,789][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:30:29,290][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:30:29,792][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:30:30,293][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:30:30,794][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:30:31,295][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:30:31,796][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:30:32,297][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:30:32,798][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:30:33,299][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:30:33,799][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:30:34,300][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:30:34,802][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:30:35,303][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:30:35,804][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:30:36,305][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:30:36,808][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:30:37,310][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:30:37,812][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:30:38,313][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:30:38,814][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:30:39,315][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:30:39,815][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:30:40,315][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:30:40,816][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:30:41,320][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:30:41,823][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:30:42,324][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:30:42,827][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:30:43,342][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:30:43,846][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:30:44,349][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:30:44,852][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21745 tokens. [2026-03-25 19:30:45,461][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.65%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:04 [2026-03-25 19:30:46,189][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:30:46,191][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:30:46,192][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:30:46,897][__main__][INFO] - Iteration 173 took 1m 13s (8.41% Gen, 90.64% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 39m 20s. Estimated total time: 61h 34m 54s. Time estimates for 10 more iterations: 12m 18s, 100 more iterations: 2h 3m 9s, 500 more iterations: 10h 15m 49s. [2026-03-25 19:30:46,900][__main__][INFO] - Starting iteration 173. [2026-03-25 19:30:47,298][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:30:47,299][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:30:53,408][__main__][INFO] - Number of regex retries in iteration 173: 0 [2026-03-25 19:30:53,409][__main__][INFO] - agents played in iteration 173 are Bob, Alice [2026-03-25 19:30:54,344][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:30:54,915][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:30:55,372][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:30:55,879][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:30:56,380][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:30:56,880][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:30:57,382][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:30:57,882][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:30:58,384][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:30:58,888][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:30:59,388][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:30:59,888][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:31:00,389][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:31:00,889][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:31:01,390][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:31:01,890][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:31:02,390][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:31:02,890][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:31:03,391][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:31:03,891][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:31:04,392][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:31:04,893][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:31:05,393][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:31:05,893][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:31:06,394][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:31:06,896][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:31:07,397][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:31:07,896][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:31:08,395][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:31:08,894][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:31:09,395][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:31:09,894][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:31:10,393][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:31:10,892][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:31:11,394][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:31:11,895][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:31:12,395][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:31:12,895][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:31:13,395][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:31:13,894][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:31:14,394][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:31:14,894][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:31:15,394][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:31:15,894][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:31:16,395][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:31:16,895][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:31:17,395][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:31:17,894][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:31:18,393][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:31:18,894][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:31:19,394][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:31:19,895][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:31:20,395][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:31:20,894][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:31:21,394][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:31:21,894][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:31:22,394][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:31:22,894][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:31:23,394][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:31:23,893][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:31:24,392][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:31:24,891][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:31:25,390][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:31:25,889][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:31:26,388][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:31:26,887][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:31:27,388][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:31:27,888][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:31:28,389][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:31:28,890][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:31:29,391][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:31:29,892][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:31:30,392][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:31:30,893][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:31:31,393][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:31:31,893][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:31:32,393][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:31:32,893][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:31:33,393][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:31:33,894][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:31:34,394][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:31:34,894][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:31:35,395][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:31:35,895][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:31:36,396][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:31:36,896][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:31:37,397][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:31:37,896][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:31:38,396][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:31:38,895][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:31:39,395][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:31:39,895][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:31:40,394][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:31:40,893][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:31:41,395][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:31:41,894][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:31:42,393][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:31:42,892][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:31:43,392][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:31:43,891][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:31:44,390][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:31:44,889][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:31:45,389][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:31:45,888][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:31:46,388][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:31:46,887][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:31:47,387][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:31:47,887][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:31:48,387][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:31:48,887][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:31:49,386][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:31:49,887][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:31:50,387][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:31:50,887][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:31:51,387][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:31:51,887][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:31:52,388][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:31:52,888][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:31:53,388][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:31:53,889][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:31:54,389][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:31:54,889][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:31:55,388][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:31:55,887][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:31:56,387][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:31:56,888][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:31:57,387][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:31:57,888][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:31:58,388][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:31:58,887][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 19:31:59,489][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:04 [2026-03-25 19:32:00,215][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:32:00,217][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:32:00,218][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:32:00,853][__main__][INFO] - Iteration 174 took 1m 13s (8.31% Gen, 90.83% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 20m 58s. Estimated total time: 61h 17m 45s. Time estimates for 10 more iterations: 12m 15s, 100 more iterations: 2h 2m 35s, 500 more iterations: 10h 12m 57s. [2026-03-25 19:32:00,855][__main__][INFO] - Starting iteration 174. [2026-03-25 19:32:01,252][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:32:01,253][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:32:03,350][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:32:07,356][__main__][INFO] - Number of regex retries in iteration 174: 1 [2026-03-25 19:32:07,357][__main__][INFO] - agents played in iteration 174 are Bob, Alice [2026-03-25 19:32:08,564][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:32:09,133][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:32:09,589][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:32:10,093][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:32:10,592][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:32:11,092][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:32:11,594][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:32:12,094][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:32:12,594][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:32:13,094][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:32:13,594][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:32:14,093][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:32:14,594][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:32:15,093][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:32:15,593][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:32:16,093][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:32:16,592][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:32:17,093][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:32:17,595][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:32:18,096][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:32:18,596][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:32:19,097][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:32:19,598][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:32:20,099][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:32:20,600][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:32:21,101][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:32:21,601][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:32:22,103][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:32:22,605][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:32:23,106][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:32:23,608][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:32:24,109][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:32:24,611][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:32:25,112][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:32:25,613][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:32:26,114][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:32:26,615][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:32:27,115][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:32:27,615][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:32:28,116][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:32:28,616][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:32:29,116][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:32:29,618][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:32:30,119][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:32:30,620][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:32:31,121][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:32:31,622][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:32:32,125][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:32:32,627][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:32:33,128][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:32:33,628][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:32:34,127][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:32:34,627][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:32:35,127][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:32:35,627][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:32:36,127][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:32:36,627][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:32:37,127][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:32:37,627][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:32:38,128][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:32:38,628][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:32:39,129][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:32:39,630][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:32:40,130][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:32:40,630][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:32:41,132][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:32:41,633][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:32:42,134][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:32:42,634][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:32:43,134][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:32:43,634][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:32:44,134][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:32:44,634][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:32:45,133][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:32:45,633][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:32:46,133][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:32:46,633][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:32:47,133][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:32:47,632][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:32:48,132][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:32:48,633][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:32:49,132][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:32:49,634][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:32:50,135][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:32:50,636][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:32:51,135][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:32:51,636][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:32:52,137][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:32:52,638][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:32:53,139][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:32:53,639][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:32:54,140][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:32:54,640][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:32:55,141][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:32:55,642][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:32:56,143][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:32:56,644][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:32:57,144][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:32:57,645][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:32:58,145][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:32:58,646][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:32:59,147][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:32:59,647][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:33:00,146][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:33:00,645][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:33:01,145][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:33:01,646][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:33:02,148][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:33:02,649][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:33:03,150][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:33:03,651][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:33:04,152][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:33:04,654][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:33:05,156][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:33:05,655][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:33:06,155][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:33:06,655][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:33:07,154][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:33:07,653][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:33:08,152][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:33:08,653][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:33:09,154][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:33:09,654][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:33:10,157][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:33:10,660][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:33:11,162][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:33:11,666][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:33:12,168][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:33:12,669][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:33:13,170][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 19:33:13,777][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 19:33:14,503][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:33:14,506][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:33:14,507][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:33:15,196][__main__][INFO] - Iteration 175 took 1m 13s (8.26% Gen, 90.81% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 39m 9s. Estimated total time: 61h 37m 11s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 14s, 500 more iterations: 10h 16m 11s. [2026-03-25 19:33:15,198][__main__][INFO] - Starting iteration 175. [2026-03-25 19:33:15,596][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:33:15,597][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:33:20,053][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:33:20,352][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 balls, 1, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:33:22,108][__main__][INFO] - Number of regex retries in iteration 175: 2 [2026-03-25 19:33:22,109][__main__][INFO] - agents played in iteration 175 are Bob, Alice [2026-03-25 19:33:23,043][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:33:23,617][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:33:24,079][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:33:24,584][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:33:25,086][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:33:25,588][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:33:26,092][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:33:26,593][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:33:27,096][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:33:27,597][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:33:28,098][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:33:28,600][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:33:29,102][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:33:29,605][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:33:30,107][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:33:30,609][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:33:31,111][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:33:31,612][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:33:32,113][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:33:32,614][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:33:33,116][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:33:33,617][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:33:34,118][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:33:34,618][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:33:35,120][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:33:35,621][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:33:36,124][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:33:36,626][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:33:37,127][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:33:37,629][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:33:38,130][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:33:38,631][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:33:39,133][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:33:39,635][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:33:40,135][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:33:40,635][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:33:41,135][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:33:41,636][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:33:42,137][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:33:42,637][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:33:43,138][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:33:43,638][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:33:44,140][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:33:44,643][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:33:45,146][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:33:45,649][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:33:46,150][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:33:46,652][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:33:47,154][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:33:47,656][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:33:48,159][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:33:48,660][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:33:49,162][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:33:49,663][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:33:50,164][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:33:50,666][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:33:51,168][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:33:51,670][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:33:52,170][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:33:52,670][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:33:53,172][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:33:53,672][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:33:54,173][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:33:54,674][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:33:55,175][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:33:55,676][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:33:56,175][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:33:56,676][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:33:57,177][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:33:57,678][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:33:58,179][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:33:58,680][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:33:59,181][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:33:59,683][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:34:00,185][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:34:00,686][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:34:01,187][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:34:01,690][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:34:02,191][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:34:02,692][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:34:03,193][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:34:03,696][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:34:04,197][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:34:04,698][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:34:05,198][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:34:05,699][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:34:06,201][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:34:06,702][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:34:07,205][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:34:07,706][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:34:08,209][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:34:08,711][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:34:09,214][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:34:09,716][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:34:10,219][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:34:10,721][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:34:11,223][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:34:11,727][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:34:12,228][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:34:12,729][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:34:13,230][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:34:13,730][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:34:14,232][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:34:14,733][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:34:15,234][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:34:15,736][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:34:16,238][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:34:16,740][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:34:17,241][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:34:17,746][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:34:18,249][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:34:18,752][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:34:19,254][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:34:19,756][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:34:20,258][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:34:20,759][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:34:21,259][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:34:21,761][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:34:22,262][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:34:22,764][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:34:23,264][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:34:23,766][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:34:24,268][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:34:24,769][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:34:25,270][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:34:25,772][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:34:26,272][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:34:26,774][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:34:27,275][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:34:27,777][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21709 tokens. [2026-03-25 19:34:28,386][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-25 19:34:29,113][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:34:29,115][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:34:29,117][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:34:29,802][__main__][INFO] - Iteration 176 took 1m 14s (8.77% Gen, 90.30% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 51m 0s. Estimated total time: 61h 50m 17s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 40s, 500 more iterations: 10h 18m 22s. [2026-03-25 19:34:29,804][__main__][INFO] - Starting iteration 176. [2026-03-25 19:34:30,211][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:34:30,211][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:34:36,613][__main__][INFO] - Number of regex retries in iteration 176: 0 [2026-03-25 19:34:36,614][__main__][INFO] - agents played in iteration 176 are Bob, Alice [2026-03-25 19:34:37,805][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:34:38,384][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:34:38,841][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:34:39,345][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:34:39,845][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:34:40,344][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:34:40,845][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:34:41,349][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:34:41,850][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:34:42,350][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:34:42,853][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:34:43,355][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:34:43,856][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:34:44,357][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:34:44,859][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:34:45,360][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:34:45,862][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:34:46,365][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:34:46,866][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:34:47,367][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:34:47,867][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:34:48,368][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:34:48,869][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:34:49,370][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:34:49,870][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:34:50,370][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:34:50,869][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:34:51,369][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:34:51,868][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:34:52,368][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:34:52,867][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:34:53,366][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:34:53,868][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:34:54,367][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:34:54,867][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:34:55,368][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:34:55,869][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:34:56,369][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:34:56,868][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:34:57,369][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:34:57,869][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:34:58,369][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:34:58,869][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:34:59,370][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:34:59,869][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:35:00,369][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:35:00,870][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:35:01,370][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:35:01,870][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:35:02,369][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:35:02,869][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:35:03,369][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:35:03,869][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:35:04,368][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:35:04,868][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:35:05,368][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:35:05,867][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:35:06,367][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:35:06,868][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:35:07,369][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:35:07,870][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:35:08,371][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:35:08,873][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:35:09,373][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:35:09,874][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:35:10,375][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:35:10,875][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:35:11,378][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:35:11,879][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:35:12,379][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:35:12,879][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:35:13,379][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:35:13,878][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:35:14,379][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:35:14,879][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:35:15,380][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:35:15,880][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:35:16,380][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:35:16,880][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:35:17,381][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:35:17,881][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:35:18,382][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:35:18,882][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:35:19,382][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:35:19,881][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:35:20,380][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:35:20,880][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:35:21,380][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:35:21,880][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:35:22,380][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:35:22,879][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:35:23,378][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:35:23,876][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:35:24,375][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:35:24,874][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:35:25,373][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:35:25,873][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:35:26,372][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:35:26,873][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:35:27,372][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:35:27,873][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:35:28,373][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:35:28,873][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:35:29,374][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:35:29,873][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:35:30,373][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:35:30,873][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:35:31,373][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:35:31,873][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:35:32,373][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:35:32,874][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:35:33,375][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:35:33,875][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:35:34,375][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:35:34,874][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:35:35,373][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:35:35,873][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:35:36,372][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:35:36,872][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:35:37,373][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:35:37,873][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:35:38,372][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:35:38,873][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:35:39,387][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:35:39,889][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:35:40,392][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:35:40,895][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:35:41,399][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:35:41,903][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:35:42,406][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 19:35:43,023][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 19:35:43,754][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:35:43,756][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:35:43,758][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:35:44,394][__main__][INFO] - Iteration 177 took 1m 14s (8.63% Gen, 90.51% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 48m 39s. Estimated total time: 61h 49m 10s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 38s, 500 more iterations: 10h 18m 11s. [2026-03-25 19:35:44,396][__main__][INFO] - Starting iteration 177. [2026-03-25 19:35:44,794][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:35:44,795][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:35:51,204][__main__][INFO] - Number of regex retries in iteration 177: 0 [2026-03-25 19:35:51,204][__main__][INFO] - agents played in iteration 177 are Bob, Alice [2026-03-25 19:35:52,111][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:35:52,687][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:35:53,147][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:35:53,655][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:35:54,158][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:35:54,661][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:35:55,164][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:35:55,666][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:35:56,169][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:35:56,671][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:35:57,171][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:35:57,670][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:35:58,171][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:35:58,671][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:35:59,170][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:35:59,670][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:36:00,170][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:36:00,671][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:36:01,170][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:36:01,670][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:36:02,169][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:36:02,669][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:36:03,169][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:36:03,669][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:36:04,169][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:36:04,669][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:36:05,170][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:36:05,670][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:36:06,170][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:36:06,672][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:36:07,172][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:36:07,673][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:36:08,173][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:36:08,673][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:36:09,172][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:36:09,671][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:36:10,170][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:36:10,669][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:36:11,169][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:36:11,670][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:36:12,170][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:36:12,669][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:36:13,169][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:36:13,669][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:36:14,169][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:36:14,669][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:36:15,169][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:36:15,670][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:36:16,169][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:36:16,669][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:36:17,170][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:36:17,671][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:36:18,171][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:36:18,672][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:36:19,172][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:36:19,672][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:36:20,172][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:36:20,673][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:36:21,173][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:36:21,674][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:36:22,174][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:36:22,674][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:36:23,174][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:36:23,675][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:36:24,175][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:36:24,676][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:36:25,179][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:36:25,681][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:36:26,185][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:36:26,688][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:36:27,191][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:36:27,694][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:36:28,195][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:36:28,697][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:36:29,197][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:36:29,697][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:36:30,197][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:36:30,698][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:36:31,198][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:36:31,698][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:36:32,197][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:36:32,697][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:36:33,196][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:36:33,695][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:36:34,196][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:36:34,695][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:36:35,194][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:36:35,694][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:36:36,193][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:36:36,692][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:36:37,193][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:36:37,694][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:36:38,194][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:36:38,695][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:36:39,195][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:36:39,695][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:36:40,196][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:36:40,696][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:36:41,197][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:36:41,699][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:36:42,199][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:36:42,698][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:36:43,197][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:36:43,697][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:36:44,197][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:36:44,697][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:36:45,197][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:36:45,696][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:36:46,195][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:36:46,695][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:36:47,195][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:36:47,694][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:36:48,195][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:36:48,695][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:36:49,195][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:36:49,695][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:36:50,194][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:36:50,694][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:36:51,194][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:36:51,694][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:36:52,194][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:36:52,694][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:36:53,194][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:36:53,694][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:36:54,190][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:36:54,691][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:36:55,192][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:36:55,693][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:36:56,193][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:36:56,693][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21691 tokens. [2026-03-25 19:36:57,301][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:04 [2026-03-25 19:36:58,029][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:36:58,031][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:36:58,033][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:36:58,734][__main__][INFO] - Iteration 178 took 1m 13s (8.67% Gen, 90.38% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 35m 17s. Estimated total time: 61h 37m 2s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 14s, 500 more iterations: 10h 16m 10s. [2026-03-25 19:36:58,736][__main__][INFO] - Starting iteration 178. [2026-03-25 19:36:59,134][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:36:59,135][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:37:06,103][__main__][INFO] - Number of regex retries in iteration 178: 0 [2026-03-25 19:37:06,104][__main__][INFO] - agents played in iteration 178 are Bob, Alice [2026-03-25 19:37:07,004][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:37:07,577][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:37:08,035][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:37:08,540][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:37:09,042][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:37:09,544][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:37:10,046][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:37:10,548][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:37:11,050][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:37:11,554][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:37:12,056][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:37:12,558][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:37:13,061][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:37:13,563][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:37:14,064][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:37:14,568][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:37:15,070][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:37:15,571][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:37:16,071][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:37:16,571][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:37:17,071][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:37:17,571][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:37:18,071][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:37:18,572][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:37:19,072][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:37:19,572][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:37:20,074][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:37:20,574][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:37:21,075][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:37:21,575][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:37:22,077][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:37:22,578][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:37:23,079][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:37:23,579][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:37:24,079][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:37:24,580][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:37:25,082][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:37:25,583][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:37:26,085][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:37:26,586][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:37:27,088][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:37:27,590][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:37:28,094][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:37:28,597][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:37:29,099][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:37:29,601][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:37:30,105][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:37:30,608][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:37:31,110][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:37:31,613][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:37:32,114][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:37:32,615][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:37:33,117][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:37:33,618][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:37:34,119][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:37:34,620][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:37:35,120][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:37:35,621][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:37:36,121][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:37:36,622][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:37:37,123][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:37:37,624][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:37:38,124][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:37:38,625][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:37:39,126][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:37:39,628][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:37:40,129][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:37:40,631][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:37:41,133][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:37:41,636][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:37:42,138][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:37:42,639][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:37:43,140][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:37:43,642][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:37:44,143][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:37:44,645][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:37:45,145][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:37:45,649][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:37:46,150][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:37:46,652][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:37:47,153][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:37:47,654][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:37:48,154][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:37:48,655][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:37:49,155][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:37:49,656][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:37:50,156][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:37:50,656][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:37:51,155][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:37:51,655][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:37:52,156][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:37:52,657][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:37:53,158][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:37:53,659][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:37:54,161][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:37:54,661][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:37:55,163][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:37:55,665][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:37:56,167][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:37:56,668][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:37:57,170][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:37:57,671][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:37:58,172][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:37:58,673][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:37:59,178][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:37:59,679][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:38:00,181][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:38:00,684][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:38:01,189][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:38:01,691][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:38:02,194][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:38:02,696][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:38:03,198][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:38:03,700][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:38:04,201][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:38:04,702][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:38:05,212][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:38:05,715][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:38:06,217][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:38:06,719][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:38:07,221][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:38:07,723][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:38:08,225][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:38:08,726][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:38:09,227][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:38:09,729][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:38:10,230][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:38:10,731][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:38:11,237][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:38:11,738][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21743 tokens. [2026-03-25 19:38:12,347][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-25 19:38:13,074][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:38:13,076][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:38:13,078][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:38:13,766][__main__][INFO] - Iteration 179 took 1m 14s (9.34% Gen, 89.74% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 58h 8m 35s. Estimated total time: 62h 11m 36s. Time estimates for 10 more iterations: 12m 26s, 100 more iterations: 2h 4m 23s, 500 more iterations: 10h 21m 56s. [2026-03-25 19:38:13,768][__main__][INFO] - Starting iteration 179. [2026-03-25 19:38:14,168][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:38:14,168][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:38:20,529][__main__][INFO] - Number of regex retries in iteration 179: 0 [2026-03-25 19:38:20,529][__main__][INFO] - agents played in iteration 179 are Bob, Alice [2026-03-25 19:38:21,432][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:38:22,004][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:38:22,461][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:38:22,966][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:38:23,466][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:38:23,967][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:38:24,466][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:38:24,966][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:38:25,465][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:38:25,966][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:38:26,469][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:38:26,969][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:38:27,470][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:38:27,970][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:38:28,470][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:38:28,970][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:38:29,471][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:38:29,971][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:38:30,471][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:38:30,972][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:38:31,473][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:38:31,973][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:38:32,473][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:38:32,974][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:38:33,474][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:38:33,975][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:38:34,475][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:38:34,975][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:38:35,475][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:38:35,976][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:38:36,477][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:38:36,979][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:38:37,479][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:38:37,979][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:38:38,479][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:38:38,978][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:38:39,478][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:38:39,977][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:38:40,478][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:38:40,978][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:38:41,481][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:38:41,981][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:38:42,479][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:38:42,979][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:38:43,478][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:38:43,978][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:38:44,478][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:38:44,977][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:38:45,477][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:38:45,976][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:38:46,477][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:38:46,976][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:38:47,476][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:38:47,977][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:38:48,477][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:38:48,977][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:38:49,477][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:38:49,978][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:38:50,479][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:38:50,980][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:38:51,480][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:38:51,981][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:38:52,481][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:38:52,982][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:38:53,483][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:38:53,984][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:38:54,484][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:38:54,983][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:38:55,484][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:38:55,984][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:38:56,486][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:38:56,987][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:38:57,487][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:38:57,987][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:38:58,488][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:38:58,990][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:38:59,490][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:38:59,991][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:39:00,492][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:39:00,993][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:39:01,493][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:39:01,994][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:39:02,495][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:39:02,995][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:39:03,496][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:39:03,996][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:39:04,496][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:39:04,997][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:39:05,498][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:39:05,998][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:39:06,498][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:39:06,997][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:39:07,498][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:39:07,997][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:39:08,497][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:39:08,996][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:39:09,495][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:39:09,994][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:39:10,495][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:39:10,996][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:39:11,499][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:39:11,999][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:39:12,500][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:39:13,000][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:39:13,501][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:39:14,001][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:39:14,502][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:39:15,002][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:39:15,502][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:39:16,003][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:39:16,503][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:39:17,003][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:39:17,503][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:39:18,004][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:39:18,504][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:39:19,005][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:39:19,507][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:39:20,008][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:39:20,508][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:39:21,009][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:39:21,510][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:39:22,010][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:39:22,511][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:39:23,012][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:39:23,513][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:39:24,015][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:39:24,516][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:39:25,017][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:39:25,517][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:39:26,018][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 19:39:26,624][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:04 [2026-03-25 19:39:27,346][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:39:27,348][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:39:27,350][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:39:27,998][__main__][INFO] - Iteration 180 took 1m 13s (8.62% Gen, 90.51% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 27m 16s. Estimated total time: 61h 31m 31s. Time estimates for 10 more iterations: 12m 18s, 100 more iterations: 2h 3m 3s, 500 more iterations: 10h 15m 15s. [2026-03-25 19:39:27,999][__main__][INFO] - Starting iteration 180. [2026-03-25 19:39:28,400][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:39:28,401][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:39:35,097][__main__][INFO] - Number of regex retries in iteration 180: 0 [2026-03-25 19:39:35,097][__main__][INFO] - agents played in iteration 180 are Bob, Alice [2026-03-25 19:39:35,996][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:39:36,569][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:39:37,030][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:39:37,536][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:39:38,038][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:39:38,538][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:39:39,040][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:39:39,541][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:39:40,043][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:39:40,544][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:39:41,046][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:39:41,549][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:39:42,050][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:39:42,551][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:39:43,058][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:39:43,560][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:39:44,064][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:39:44,566][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:39:45,072][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:39:45,575][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:39:46,077][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:39:46,579][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:39:47,081][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:39:47,583][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:39:48,086][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:39:48,593][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:39:49,094][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:39:49,595][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:39:50,096][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:39:50,596][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:39:51,096][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:39:51,596][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:39:52,096][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:39:52,597][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:39:53,097][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:39:53,598][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:39:54,098][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:39:54,600][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:39:55,101][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:39:55,602][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:39:56,102][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:39:56,603][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:39:57,104][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:39:57,605][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:39:58,106][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:39:58,606][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:39:59,107][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:39:59,608][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:40:00,108][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:40:00,609][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:40:01,110][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:40:01,611][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:40:02,111][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:40:02,612][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:40:03,112][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:40:03,613][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:40:04,113][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:40:04,614][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:40:05,114][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:40:05,614][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:40:06,114][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:40:06,614][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:40:07,117][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:40:07,617][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:40:08,118][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:40:08,618][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:40:09,118][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:40:09,618][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:40:10,119][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:40:10,620][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:40:11,120][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:40:11,623][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:40:12,124][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:40:12,625][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:40:13,126][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:40:13,627][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:40:14,128][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:40:14,629][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:40:15,130][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:40:15,631][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:40:16,131][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:40:16,632][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:40:17,135][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:40:17,636][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:40:18,137][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:40:18,641][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:40:19,142][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:40:19,643][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:40:20,145][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:40:20,647][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:40:21,147][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:40:21,648][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:40:22,148][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:40:22,649][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:40:23,149][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:40:23,649][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:40:24,150][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:40:24,650][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:40:25,150][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:40:25,651][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:40:26,152][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:40:26,652][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:40:27,154][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:40:27,653][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:40:28,153][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:40:28,653][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:40:29,153][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:40:29,653][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:40:30,153][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:40:30,653][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:40:31,152][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:40:31,652][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:40:32,152][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:40:32,652][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:40:33,152][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:40:33,653][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:40:34,154][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:40:34,654][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:40:35,154][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:40:35,654][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:40:36,154][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:40:36,654][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:40:37,153][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:40:37,653][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:40:38,153][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:40:38,653][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:40:39,153][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:40:39,653][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:40:40,153][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:40:40,653][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21709 tokens. [2026-03-25 19:40:41,261][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.36%, ΔTime: 00:01:04 [2026-03-25 19:40:41,990][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:40:41,992][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:40:41,993][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:40:42,692][__main__][INFO] - Iteration 181 took 1m 14s (9.01% Gen, 90.04% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 49m 7s. Estimated total time: 61h 54m 36s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 49s, 500 more iterations: 10h 19m 6s. [2026-03-25 19:40:42,694][__main__][INFO] - Starting iteration 181. [2026-03-25 19:40:43,095][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:40:43,096][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:40:49,425][__main__][INFO] - Number of regex retries in iteration 181: 0 [2026-03-25 19:40:49,425][__main__][INFO] - agents played in iteration 181 are Bob, Alice [2026-03-25 19:40:50,327][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:40:50,900][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:40:51,359][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:40:51,864][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:40:52,366][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:40:52,867][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:40:53,368][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:40:53,868][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:40:54,369][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:40:54,881][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:40:55,383][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:40:55,884][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:40:56,386][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:40:56,887][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:40:57,389][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:40:57,890][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:40:58,391][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:40:58,891][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:40:59,395][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:40:59,897][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:41:00,398][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:41:00,904][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:41:01,406][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:41:01,908][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:41:02,409][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:41:02,911][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:41:03,413][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:41:03,913][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:41:04,414][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:41:04,915][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:41:05,415][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:41:05,916][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:41:06,416][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:41:06,919][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:41:07,419][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:41:07,918][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:41:08,418][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:41:08,917][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:41:09,418][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:41:09,917][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:41:10,419][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:41:10,918][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:41:11,421][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:41:11,922][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:41:12,421][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:41:12,922][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:41:13,422][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:41:13,923][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:41:14,423][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:41:14,922][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:41:15,421][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:41:15,921][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:41:16,422][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:41:16,922][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:41:17,421][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:41:17,921][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:41:18,421][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:41:18,921][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:41:19,421][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:41:19,921][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:41:20,421][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:41:20,921][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:41:21,421][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:41:21,921][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:41:22,421][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:41:22,921][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:41:23,422][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:41:23,923][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:41:24,423][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:41:24,924][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:41:25,423][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:41:25,924][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:41:26,426][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:41:26,927][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:41:27,427][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:41:27,928][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:41:28,428][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:41:28,927][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:41:29,428][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:41:29,928][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:41:30,428][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:41:30,929][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:41:31,430][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:41:31,931][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:41:32,432][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:41:32,933][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:41:33,434][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:41:33,935][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:41:34,436][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:41:34,937][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:41:35,437][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:41:35,938][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:41:36,438][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:41:36,939][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:41:37,441][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:41:37,942][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:41:38,443][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:41:38,943][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:41:39,443][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:41:39,944][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:41:40,445][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:41:40,945][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:41:41,446][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:41:41,948][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:41:42,448][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:41:42,949][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:41:43,450][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:41:43,951][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:41:44,451][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:41:44,952][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:41:45,453][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:41:45,953][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:41:46,454][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:41:46,955][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:41:47,455][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:41:47,955][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:41:48,455][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:41:48,955][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:41:49,455][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:41:49,955][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:41:50,456][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:41:50,956][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:41:51,455][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:41:51,955][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:41:52,455][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:41:52,956][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:41:53,456][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:41:53,957][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:41:54,457][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:41:54,958][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 19:41:55,570][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 19:41:56,329][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:41:56,331][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:41:56,332][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:41:57,036][__main__][INFO] - Iteration 182 took 1m 13s (8.56% Gen, 90.49% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 30m 21s. Estimated total time: 61h 37m 4s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 14s, 500 more iterations: 10h 16m 10s. [2026-03-25 19:41:57,038][__main__][INFO] - Starting iteration 182. [2026-03-25 19:41:57,438][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:41:57,438][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:41:59,149][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:42:04,131][__main__][INFO] - Number of regex retries in iteration 182: 1 [2026-03-25 19:42:04,131][__main__][INFO] - agents played in iteration 182 are Bob, Alice [2026-03-25 19:42:05,035][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:42:05,618][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:42:06,076][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:42:06,582][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:42:07,084][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:42:07,588][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:42:08,091][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:42:08,593][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:42:09,094][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:42:09,595][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:42:10,095][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:42:10,593][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:42:11,092][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:42:11,593][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:42:12,093][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:42:12,591][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:42:13,090][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:42:13,590][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:42:14,090][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:42:14,591][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:42:15,093][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:42:15,594][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:42:16,094][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:42:16,595][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:42:17,095][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:42:17,596][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:42:18,098][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:42:18,601][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:42:19,102][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:42:19,604][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:42:20,108][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:42:20,611][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:42:21,113][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:42:21,615][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:42:22,116][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:42:22,617][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:42:23,117][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:42:23,619][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:42:24,120][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:42:24,622][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:42:25,123][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:42:25,625][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:42:26,124][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:42:26,624][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:42:27,124][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:42:27,624][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:42:28,124][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:42:28,623][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:42:29,122][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:42:29,621][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:42:30,122][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:42:30,624][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:42:31,126][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:42:31,628][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:42:32,129][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:42:32,632][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:42:33,134][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:42:33,636][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:42:34,137][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:42:34,639][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:42:35,139][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:42:35,642][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:42:36,142][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:42:36,645][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:42:37,147][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:42:37,648][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:42:38,148][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:42:38,649][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:42:39,149][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:42:39,650][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:42:40,150][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:42:40,651][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:42:41,152][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:42:41,654][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:42:42,154][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:42:42,652][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:42:43,152][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:42:43,652][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:42:44,152][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:42:44,652][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:42:45,151][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:42:45,652][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:42:46,153][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:42:46,653][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:42:47,153][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:42:47,654][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:42:48,155][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:42:48,656][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:42:49,157][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:42:49,659][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:42:50,160][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:42:50,663][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:42:51,164][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:42:51,666][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:42:52,170][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:42:52,671][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:42:53,172][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:42:53,674][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:42:54,174][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:42:54,675][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:42:55,175][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:42:55,675][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:42:56,175][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:42:56,676][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:42:57,178][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:42:57,679][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:42:58,178][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:42:58,678][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:42:59,177][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:42:59,677][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:43:00,177][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:43:00,676][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:43:01,176][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:43:01,676][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:43:02,177][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:43:02,679][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:43:03,194][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:43:03,698][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:43:04,200][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:43:04,703][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:43:05,206][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:43:05,709][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:43:06,212][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:43:06,715][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:43:07,218][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:43:07,720][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:43:08,222][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:43:08,724][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:43:09,225][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:43:09,727][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 19:43:10,347][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-25 19:43:11,081][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:43:11,083][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:43:11,085][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:43:11,903][__main__][INFO] - Iteration 183 took 1m 14s (8.99% Gen, 89.91% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 55m 19s. Estimated total time: 62h 3m 17s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 6s, 500 more iterations: 10h 20m 32s. [2026-03-25 19:43:11,905][__main__][INFO] - Starting iteration 183. [2026-03-25 19:43:12,304][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:43:12,304][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:43:18,499][__main__][INFO] - Number of regex retries in iteration 183: 0 [2026-03-25 19:43:18,499][__main__][INFO] - agents played in iteration 183 are Bob, Alice [2026-03-25 19:43:19,399][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:43:19,983][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:43:20,441][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:43:20,947][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:43:21,448][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:43:21,950][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:43:22,451][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:43:22,950][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:43:23,451][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:43:23,951][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:43:24,450][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:43:24,950][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:43:25,450][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:43:25,949][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:43:26,448][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:43:26,948][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:43:27,447][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:43:27,948][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:43:28,450][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:43:28,951][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:43:29,452][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:43:29,953][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:43:30,454][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:43:30,954][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:43:31,455][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:43:31,956][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:43:32,456][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:43:32,956][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:43:33,457][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:43:33,958][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:43:34,459][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:43:34,961][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:43:35,461][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:43:35,961][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:43:36,462][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:43:36,961][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:43:37,461][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:43:37,961][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:43:38,462][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:43:38,962][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:43:39,462][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:43:39,962][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:43:40,461][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:43:40,961][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:43:41,463][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:43:41,963][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:43:42,462][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:43:42,962][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:43:43,462][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:43:43,961][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:43:44,462][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:43:44,964][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:43:45,466][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:43:45,967][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:43:46,468][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:43:46,970][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:43:47,470][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:43:47,972][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:43:48,474][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:43:48,976][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:43:49,477][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:43:49,976][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:43:50,476][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:43:50,977][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:43:51,477][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:43:51,978][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:43:52,479][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:43:52,980][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:43:53,480][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:43:53,981][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:43:54,483][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:43:54,984][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:43:55,485][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:43:55,986][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:43:56,485][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:43:56,985][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:43:57,487][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:43:57,988][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:43:58,488][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:43:58,988][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:43:59,488][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:43:59,989][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:44:00,491][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:44:00,993][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:44:01,495][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:44:01,995][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:44:02,496][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:44:02,997][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:44:03,497][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:44:03,998][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:44:04,498][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:44:04,999][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:44:05,499][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:44:05,999][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:44:06,499][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:44:06,999][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:44:07,499][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:44:07,999][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:44:08,499][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:44:08,999][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:44:09,499][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:44:10,000][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:44:10,500][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:44:11,001][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:44:11,503][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:44:12,005][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:44:12,505][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:44:13,006][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:44:13,506][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:44:14,007][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:44:14,508][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:44:15,009][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:44:15,509][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:44:16,010][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:44:16,512][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:44:17,014][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:44:17,515][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:44:18,018][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:44:18,519][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:44:19,020][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:44:19,521][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:44:20,023][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:44:20,523][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:44:21,025][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:44:21,526][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:44:22,027][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:44:22,528][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:44:23,028][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:44:23,531][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:44:24,032][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 19:44:24,654][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:04 [2026-03-25 19:44:25,382][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:44:25,384][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:44:25,385][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:44:26,021][__main__][INFO] - Iteration 184 took 1m 13s (8.40% Gen, 90.73% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 16m 42s. Estimated total time: 61h 25m 55s. Time estimates for 10 more iterations: 12m 17s, 100 more iterations: 2h 2m 51s, 500 more iterations: 10h 14m 19s. [2026-03-25 19:44:26,023][__main__][INFO] - Starting iteration 184. [2026-03-25 19:44:26,421][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:44:26,422][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:44:32,674][__main__][INFO] - Number of regex retries in iteration 184: 0 [2026-03-25 19:44:32,675][__main__][INFO] - agents played in iteration 184 are Bob, Alice [2026-03-25 19:44:33,574][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:44:34,147][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:44:34,605][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:44:35,112][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:44:35,615][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:44:36,117][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:44:36,620][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:44:37,125][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:44:37,629][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:44:38,131][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:44:38,632][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:44:39,133][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:44:39,634][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:44:40,136][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:44:40,637][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:44:41,137][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:44:41,639][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:44:42,139][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:44:42,640][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:44:43,143][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:44:43,645][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:44:44,146][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:44:44,648][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:44:45,150][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:44:45,652][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:44:46,153][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:44:46,654][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:44:47,154][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:44:47,655][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:44:48,155][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:44:48,667][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:44:49,170][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:44:49,672][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:44:50,173][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:44:50,675][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:44:51,177][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:44:51,678][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:44:52,180][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:44:52,682][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:44:53,183][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:44:53,683][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:44:54,187][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:44:54,693][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:44:55,195][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:44:55,698][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:44:56,200][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:44:56,703][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:44:57,206][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:44:57,709][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:44:58,211][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:44:58,714][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:44:59,217][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:44:59,719][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:45:00,222][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:45:00,724][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:45:01,227][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:45:01,729][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:45:02,232][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:45:02,733][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:45:03,233][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:45:03,734][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:45:04,235][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:45:04,735][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:45:05,236][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:45:05,736][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:45:06,236][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:45:06,739][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:45:07,242][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:45:07,743][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:45:08,246][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:45:08,748][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:45:09,251][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:45:09,754][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:45:10,257][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:45:10,758][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:45:11,260][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:45:11,763][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:45:12,265][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:45:12,767][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:45:13,269][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:45:13,770][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:45:14,272][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:45:14,774][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:45:15,276][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:45:15,778][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:45:16,280][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:45:16,781][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:45:17,283][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:45:17,786][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:45:18,288][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:45:18,790][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:45:19,291][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:45:19,792][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:45:20,294][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:45:20,794][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:45:21,296][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:45:21,797][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:45:22,298][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:45:22,799][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:45:23,300][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:45:23,801][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:45:24,302][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:45:24,805][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:45:25,307][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:45:25,810][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:45:26,312][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:45:26,815][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:45:27,317][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:45:27,819][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:45:28,321][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:45:28,823][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:45:29,326][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:45:29,828][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:45:30,331][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:45:30,833][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:45:31,336][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:45:31,838][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:45:32,340][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:45:32,842][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:45:33,345][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:45:33,847][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:45:34,349][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:45:34,850][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:45:35,351][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:45:35,851][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:45:36,351][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:45:36,852][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:45:37,352][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:45:37,853][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:45:38,354][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 19:45:38,965][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 19:45:39,692][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:45:39,694][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:45:39,696][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:45:40,432][__main__][INFO] - Iteration 185 took 1m 14s (8.45% Gen, 90.56% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 30m 5s. Estimated total time: 61h 40m 33s. Time estimates for 10 more iterations: 12m 20s, 100 more iterations: 2h 3m 21s, 500 more iterations: 10h 16m 45s. [2026-03-25 19:45:40,434][__main__][INFO] - Starting iteration 185. [2026-03-25 19:45:40,832][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:45:40,833][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:45:47,103][__main__][INFO] - Number of regex retries in iteration 185: 0 [2026-03-25 19:45:47,103][__main__][INFO] - agents played in iteration 185 are Bob, Alice [2026-03-25 19:45:48,006][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:45:48,587][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:45:49,045][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:45:49,551][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:45:50,054][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:45:50,556][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:45:51,058][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:45:51,560][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:45:52,061][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:45:52,563][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:45:53,064][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:45:53,565][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:45:54,066][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:45:54,566][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:45:55,067][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:45:55,568][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:45:56,069][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:45:56,569][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:45:57,071][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:45:57,573][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:45:58,075][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:45:58,576][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:45:59,077][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:45:59,579][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:46:00,080][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:46:00,581][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:46:01,084][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:46:01,587][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:46:02,090][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:46:02,592][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:46:03,094][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:46:03,595][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:46:04,096][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:46:04,597][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:46:05,098][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:46:05,598][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:46:06,100][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:46:06,600][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:46:07,103][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:46:07,605][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:46:08,109][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:46:08,610][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:46:09,113][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:46:09,615][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:46:10,117][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:46:10,618][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:46:11,121][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:46:11,625][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:46:12,127][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:46:12,629][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:46:13,132][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:46:13,635][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:46:14,137][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:46:14,640][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:46:15,142][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:46:15,644][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:46:16,145][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:46:16,649][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:46:17,150][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:46:17,650][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:46:18,150][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:46:18,652][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:46:19,152][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:46:19,653][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:46:20,154][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:46:20,655][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:46:21,156][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:46:21,659][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:46:22,160][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:46:22,662][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:46:23,164][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:46:23,666][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:46:24,180][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:46:24,684][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:46:25,188][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:46:25,691][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:46:26,193][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:46:26,695][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:46:27,196][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:46:27,697][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:46:28,197][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:46:28,698][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:46:29,201][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:46:29,703][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:46:30,212][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:46:30,715][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:46:31,218][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:46:31,721][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:46:32,223][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:46:32,725][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:46:33,226][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:46:33,730][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:46:34,232][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:46:34,735][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:46:35,236][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:46:35,738][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:46:36,239][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:46:36,742][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:46:37,244][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:46:37,745][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:46:38,247][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:46:38,749][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:46:39,251][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:46:39,753][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:46:40,255][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:46:40,757][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:46:41,260][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:46:41,763][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:46:42,265][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:46:42,768][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:46:43,269][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:46:43,771][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:46:44,273][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:46:44,774][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:46:45,275][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:46:45,777][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:46:46,279][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:46:46,780][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:46:47,282][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:46:47,784][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:46:48,289][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:46:48,791][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:46:49,292][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:46:49,792][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:46:50,292][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:46:50,792][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:46:51,293][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:46:51,793][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:46:52,294][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:46:52,794][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 19:46:53,406][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-25 19:46:54,135][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:46:54,137][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:46:54,139][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:46:54,840][__main__][INFO] - Iteration 186 took 1m 14s (8.47% Gen, 90.58% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 28m 42s. Estimated total time: 61h 40m 23s. Time estimates for 10 more iterations: 12m 20s, 100 more iterations: 2h 3m 20s, 500 more iterations: 10h 16m 43s. [2026-03-25 19:46:54,842][__main__][INFO] - Starting iteration 186. [2026-03-25 19:46:55,239][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:46:55,240][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:46:55,820][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:46:59,095][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:47:01,926][__main__][INFO] - Number of regex retries in iteration 186: 2 [2026-03-25 19:47:01,927][__main__][INFO] - agents played in iteration 186 are Bob, Alice [2026-03-25 19:47:02,828][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:47:03,410][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:47:03,869][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:47:04,374][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:47:04,875][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:47:05,377][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:47:05,879][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:47:06,380][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:47:06,882][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:47:07,384][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:47:07,891][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:47:08,394][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:47:08,898][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:47:09,400][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:47:09,902][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:47:10,405][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:47:10,909][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:47:11,414][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:47:11,917][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:47:12,419][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:47:12,920][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:47:13,422][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:47:13,925][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:47:14,427][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:47:14,927][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:47:15,429][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:47:15,930][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:47:16,432][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:47:16,934][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:47:17,435][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:47:17,936][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:47:18,437][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:47:18,938][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:47:19,439][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:47:19,942][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:47:20,443][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:47:20,946][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:47:21,448][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:47:21,951][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:47:22,455][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:47:22,957][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:47:23,459][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:47:23,961][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:47:24,457][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:47:24,958][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:47:25,459][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:47:25,959][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:47:26,460][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:47:26,963][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:47:27,463][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:47:27,962][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:47:28,462][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:47:28,963][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:47:29,463][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:47:29,964][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:47:30,464][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:47:30,964][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:47:31,463][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:47:31,970][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:47:32,475][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:47:32,977][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:47:33,480][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:47:33,982][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:47:34,485][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:47:34,989][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:47:35,492][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:47:35,993][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:47:36,494][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:47:36,997][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:47:37,498][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:47:38,999][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:47:38,500][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:47:39,001][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:47:39,502][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:47:40,003][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:47:40,507][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:47:41,010][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:47:41,514][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:47:42,017][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:47:42,529][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:47:43,033][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:47:43,537][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:47:44,039][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:47:44,542][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:47:45,044][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:47:45,548][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:47:46,050][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:47:46,553][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:47:47,055][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:47:47,557][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:47:48,060][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:47:48,569][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:47:49,071][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:47:49,574][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:47:50,075][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:47:50,576][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:47:51,078][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:47:51,579][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:47:52,081][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:47:52,582][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:47:53,083][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:47:53,586][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:47:54,090][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:47:54,591][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:47:55,094][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:47:55,596][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:47:56,097][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:47:56,597][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:47:57,098][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:47:57,599][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:47:58,101][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:47:58,602][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:47:59,103][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:47:59,603][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:48:00,105][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:48:00,607][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:48:01,108][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:48:01,609][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:48:02,110][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:48:02,611][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:48:03,112][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:48:03,613][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:48:04,117][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:48:04,621][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:48:05,124][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:48:05,628][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:48:06,132][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:48:06,635][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:48:07,139][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:48:07,642][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21716 tokens. [2026-03-25 19:48:08,263][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.32%, Current % of VRAM taken: 60.68%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:04 [2026-03-25 19:48:08,993][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:48:08,995][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:48:08,996][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:48:09,695][__main__][INFO] - Iteration 187 took 1m 14s (8.98% Gen, 90.08% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 49m 53s. Estimated total time: 62h 2m 50s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 5s, 500 more iterations: 10h 20m 28s. [2026-03-25 19:48:09,697][__main__][INFO] - Starting iteration 187. [2026-03-25 19:48:10,099][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:48:10,100][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:48:15,043][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:48:16,506][__main__][INFO] - Number of regex retries in iteration 187: 1 [2026-03-25 19:48:16,506][__main__][INFO] - agents played in iteration 187 are Bob, Alice [2026-03-25 19:48:17,417][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:48:18,004][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:48:18,462][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:48:18,966][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:48:19,467][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:48:19,967][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:48:20,466][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:48:20,967][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:48:21,468][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:48:21,968][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:48:22,470][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:48:22,972][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:48:23,473][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:48:23,975][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:48:24,476][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:48:24,978][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:48:25,479][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:48:25,981][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:48:26,480][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:48:26,978][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:48:27,478][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:48:27,978][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:48:28,480][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:48:28,980][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:48:29,480][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:48:29,979][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:48:30,479][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:48:30,980][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:48:31,481][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:48:31,982][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:48:32,482][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:48:32,983][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:48:33,483][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:48:33,984][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:48:34,486][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:48:34,987][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:48:35,488][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:48:35,989][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:48:36,490][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:48:36,991][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:48:37,492][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:48:37,993][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:48:38,494][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:48:38,994][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:48:39,494][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:48:39,994][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:48:40,494][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:48:40,994][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:48:41,496][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:48:41,997][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:48:42,500][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:48:43,001][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:48:43,503][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:48:44,005][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:48:44,508][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:48:45,009][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:48:45,511][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:48:46,013][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:48:46,514][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:48:47,014][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:48:47,514][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:48:48,014][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:48:48,514][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:48:49,014][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:48:49,513][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:48:50,013][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:48:50,514][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:48:51,015][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:48:51,516][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:48:52,016][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:48:52,517][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:48:53,018][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:48:53,519][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:48:54,020][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:48:54,523][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:48:55,024][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:48:55,525][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:48:56,026][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:48:56,529][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:48:57,030][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:48:57,532][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:48:58,034][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:48:58,534][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:48:59,034][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:48:59,534][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:49:00,034][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:49:00,534][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:49:01,034][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:49:01,534][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:49:02,035][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:49:02,535][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:49:03,036][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:49:03,536][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:49:04,038][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:49:04,538][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:49:05,038][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:49:05,538][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:49:06,038][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:49:06,539][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:49:07,040][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:49:07,542][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:49:08,042][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:49:08,542][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:49:09,042][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:49:09,541][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:49:10,041][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:49:10,541][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:49:11,042][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:49:11,544][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:49:12,044][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:49:12,545][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:49:13,045][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:49:13,546][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:49:14,046][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:49:14,549][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:49:15,050][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:49:15,552][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:49:16,054][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:49:16,555][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:49:17,057][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:49:17,558][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:49:18,061][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:49:18,561][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:49:19,060][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:49:19,559][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:49:20,058][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:49:20,557][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:49:21,057][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:49:21,556][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:49:22,055][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 19:49:22,677][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.16%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 19:49:23,407][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:49:23,409][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:49:23,410][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:49:24,053][__main__][INFO] - Iteration 188 took 1m 13s (8.66% Gen, 90.47% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 23m 33s. Estimated total time: 61h 37m 44s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 15s, 500 more iterations: 10h 16m 17s. [2026-03-25 19:49:24,055][__main__][INFO] - Starting iteration 188. [2026-03-25 19:49:24,456][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:49:24,456][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:49:31,073][__main__][INFO] - Number of regex retries in iteration 188: 0 [2026-03-25 19:49:31,074][__main__][INFO] - agents played in iteration 188 are Bob, Alice [2026-03-25 19:49:31,979][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:49:32,563][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:49:33,020][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:49:33,526][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:49:34,027][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:49:34,528][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:49:35,031][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:49:35,532][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:49:36,034][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:49:36,535][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:49:37,035][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:49:37,536][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:49:38,036][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:49:38,536][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:49:39,037][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:49:39,537][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:49:40,038][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:49:40,539][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:49:41,042][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:49:41,545][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:49:42,047][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:49:42,549][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:49:43,050][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:49:43,551][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:49:44,053][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:49:44,554][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:49:45,056][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:49:45,556][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:49:46,057][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:49:46,559][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:49:47,060][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:49:47,562][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:49:48,064][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:49:48,565][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:49:49,067][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:49:49,567][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:49:50,069][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:49:50,570][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:49:51,071][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:49:51,572][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:49:52,073][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:49:52,574][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:49:53,077][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:49:53,579][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:49:54,080][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:49:54,582][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:49:55,084][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:49:55,586][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:49:56,089][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:49:56,590][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:49:57,091][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:49:57,592][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:49:58,094][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:49:58,595][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:49:59,096][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:49:59,597][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:50:00,097][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:50:00,599][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:50:01,100][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:50:01,600][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:50:02,101][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:50:02,603][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:50:03,104][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:50:03,606][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:50:04,107][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:50:04,610][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:50:05,111][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:50:05,611][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:50:06,113][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:50:06,614][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:50:07,114][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:50:07,616][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:50:08,116][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:50:08,617][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:50:09,117][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:50:09,617][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:50:10,119][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:50:10,619][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:50:11,120][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:50:11,623][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:50:12,123][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:50:12,624][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:50:13,127][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:50:13,628][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:50:14,130][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:50:14,632][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:50:15,134][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:50:15,635][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:50:16,137][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:50:16,639][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:50:17,140][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:50:17,640][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:50:18,141][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:50:18,642][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:50:19,144][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:50:19,645][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:50:20,146][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:50:20,647][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:50:21,150][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:50:21,652][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:50:22,155][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:50:22,656][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:50:23,158][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:50:23,659][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:50:24,160][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:50:24,661][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:50:25,163][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:50:25,665][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:50:26,166][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:50:26,669][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:50:27,171][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:50:27,673][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:50:28,174][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:50:28,677][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:50:29,178][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:50:29,679][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:50:30,180][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:50:30,682][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:50:31,184][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:50:31,687][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:50:32,188][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:50:32,690][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:50:33,193][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:50:33,695][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:50:34,197][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:50:34,698][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:50:35,199][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:50:35,699][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:50:36,200][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:50:36,702][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 19:50:37,329][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 19:50:38,071][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:50:38,074][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:50:38,075][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:50:38,711][__main__][INFO] - Iteration 189 took 1m 14s (8.91% Gen, 90.23% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 37m 22s. Estimated total time: 61h 52m 48s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 45s, 500 more iterations: 10h 18m 48s. [2026-03-25 19:50:38,713][__main__][INFO] - Starting iteration 189. [2026-03-25 19:50:39,114][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:50:39,115][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:50:39,694][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:50:44,012][mllm.models.large_language_model_local][WARNING] - Response Given the current per-item values, it seems that Alice values hats and books more, and both of us value balls the same. To maximize our points, we should try to capture all the balls since they have the highest value for both of us. Here is a strategic proposal: Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:50:45,851][__main__][INFO] - Number of regex retries in iteration 189: 2 [2026-03-25 19:50:45,852][__main__][INFO] - agents played in iteration 189 are Bob, Alice [2026-03-25 19:50:46,752][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:50:47,325][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:50:47,781][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:50:48,285][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:50:48,785][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:50:49,285][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:50:49,786][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:50:50,287][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:50:50,788][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:50:51,287][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:50:51,791][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:50:52,293][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:50:52,795][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:50:53,296][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:50:53,799][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:50:54,300][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:50:54,802][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:50:55,303][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:50:55,804][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:50:56,304][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:50:56,804][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:50:57,305][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:50:57,806][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:50:58,307][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:50:58,810][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:50:59,311][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:50:59,812][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:51:00,313][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:51:00,815][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:51:01,316][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:51:01,816][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:51:02,318][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:51:02,818][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:51:03,319][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:51:03,820][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:51:04,321][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:51:04,820][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:51:05,321][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:51:05,822][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:51:06,323][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:51:06,823][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:51:07,324][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:51:07,827][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:51:08,330][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:51:08,832][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:51:09,334][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:51:09,837][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:51:10,339][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:51:10,843][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:51:11,348][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:51:11,850][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:51:12,353][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:51:12,855][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:51:13,356][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:51:13,859][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:51:14,360][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:51:14,862][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:51:15,363][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:51:15,864][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:51:16,365][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:51:16,865][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:51:17,368][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:51:17,870][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:51:18,370][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:51:18,871][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:51:19,372][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:51:19,872][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:51:20,372][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:51:20,872][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:51:21,373][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:51:21,873][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:51:22,373][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:51:22,873][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:51:23,373][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:51:23,876][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:51:24,378][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:51:24,881][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:51:25,383][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:51:25,886][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:51:26,389][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:51:26,892][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:51:27,395][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:51:27,896][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:51:28,397][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:51:28,896][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:51:29,397][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:51:29,899][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:51:30,399][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:51:30,900][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:51:31,401][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:51:31,902][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:51:32,403][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:51:32,905][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:51:33,408][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:51:33,909][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:51:34,413][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:51:34,915][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:51:35,416][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:51:35,917][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:51:36,418][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:51:36,919][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:51:37,420][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:51:37,921][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:51:38,421][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:51:38,922][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:51:39,422][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:51:39,924][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:51:40,427][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:51:40,929][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:51:41,436][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:51:41,938][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:51:42,440][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:51:42,943][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:51:43,445][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:51:43,947][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:51:44,448][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:51:44,950][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:51:45,452][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:51:45,955][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:51:46,457][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:51:46,958][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:51:47,460][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:51:47,960][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:51:48,461][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:51:48,963][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:51:49,463][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:51:49,965][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:51:50,465][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:51:50,967][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:51:51,468][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 19:51:52,082][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:04 [2026-03-25 19:51:52,810][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:51:52,813][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:51:52,814][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:51:53,530][__main__][INFO] - Iteration 190 took 1m 14s (9.05% Gen, 89.98% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 44m 8s. Estimated total time: 62h 0m 49s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 1s, 500 more iterations: 10h 20m 8s. [2026-03-25 19:51:53,532][__main__][INFO] - Starting iteration 190. [2026-03-25 19:51:53,934][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:51:53,935][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:51:54,519][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:51:55,585][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:52:00,380][__main__][INFO] - Number of regex retries in iteration 190: 2 [2026-03-25 19:52:00,381][__main__][INFO] - agents played in iteration 190 are Bob, Alice [2026-03-25 19:52:01,298][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:52:01,880][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:52:02,334][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:52:02,835][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:52:03,333][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:52:03,831][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:52:04,328][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:52:04,827][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:52:05,325][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:52:05,822][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:52:06,325][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:52:06,826][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:52:07,330][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:52:07,832][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:52:08,333][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:52:08,835][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:52:09,337][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:52:09,838][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:52:10,341][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:52:10,844][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:52:11,350][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:52:11,853][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:52:12,355][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:52:12,857][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:52:13,359][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:52:13,861][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:52:14,363][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:52:14,865][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:52:15,366][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:52:15,867][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:52:16,368][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:52:16,870][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:52:17,372][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:52:17,874][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:52:18,380][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:52:18,883][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:52:19,387][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:52:19,890][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:52:20,393][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:52:20,896][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:52:21,398][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:52:21,900][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:52:22,402][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:52:22,905][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:52:23,407][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:52:23,910][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:52:24,413][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:52:24,915][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:52:25,418][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:52:25,920][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:52:26,423][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:52:26,924][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:52:27,425][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:52:27,929][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:52:28,431][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:52:28,933][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:52:29,435][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:52:29,937][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:52:30,439][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:52:30,940][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:52:31,443][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:52:31,944][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:52:32,446][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:52:32,947][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:52:33,449][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:52:33,951][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:52:34,451][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:52:34,949][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:52:35,448][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:52:35,946][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:52:36,444][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:52:36,941][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:52:37,438][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:52:37,935][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:52:38,436][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:52:38,937][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:52:39,438][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:52:39,939][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:52:40,440][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:52:40,941][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:52:41,444][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:52:41,947][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:52:42,450][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:52:42,951][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:52:43,454][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:52:43,957][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:52:44,459][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:52:44,962][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:52:45,464][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:52:45,966][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:52:46,467][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:52:46,969][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:52:47,470][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:52:47,972][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:52:48,473][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:52:48,974][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:52:49,476][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:52:49,977][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:52:50,479][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:52:50,981][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:52:51,483][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:52:51,985][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:52:52,488][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:52:52,990][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:52:53,493][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:52:53,995][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:52:54,497][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:52:54,998][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:52:55,499][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:52:56,000][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:52:56,502][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:52:57,003][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:52:57,505][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:52:58,008][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:52:58,511][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:52:59,013][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:52:59,517][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:53:00,020][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:53:00,522][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:53:01,024][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:53:01,528][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:53:02,031][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:53:02,534][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:53:03,036][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:53:03,537][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:53:04,039][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:53:04,540][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:53:05,043][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:53:05,545][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:53:06,047][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 19:53:06,670][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.30%, ΔTime: 00:01:04 [2026-03-25 19:53:07,398][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:53:07,400][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:53:07,401][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:53:08,080][__main__][INFO] - Iteration 191 took 1m 14s (8.69% Gen, 90.39% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 29m 23s. Estimated total time: 61h 47m 18s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 34s, 500 more iterations: 10h 17m 53s. [2026-03-25 19:53:08,082][__main__][INFO] - Starting iteration 191. [2026-03-25 19:53:08,485][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:53:08,486][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:53:14,646][__main__][INFO] - Number of regex retries in iteration 191: 0 [2026-03-25 19:53:14,647][__main__][INFO] - agents played in iteration 191 are Bob, Alice [2026-03-25 19:53:15,549][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:53:16,134][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:53:16,591][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:53:17,097][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:53:17,599][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:53:18,100][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:53:18,601][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:53:19,103][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:53:19,605][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:53:20,106][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:53:20,609][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:53:21,112][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:53:21,614][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:53:22,117][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:53:22,620][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:53:23,122][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:53:23,624][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:53:24,126][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:53:24,632][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:53:25,135][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:53:25,638][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:53:26,141][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:53:26,643][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:53:27,146][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:53:27,650][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:53:28,153][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:53:28,655][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:53:29,158][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:53:29,660][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:53:30,162][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:53:30,665][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:53:31,167][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:53:31,670][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:53:32,172][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:53:32,674][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:53:33,175][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:53:33,677][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:53:34,179][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:53:34,680][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:53:35,181][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:53:35,682][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:53:36,185][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:53:36,688][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:53:37,193][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:53:37,698][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:53:38,200][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:53:38,702][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:53:39,205][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:53:39,709][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:53:40,211][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:53:40,713][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:53:41,217][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:53:41,720][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:53:42,221][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:53:42,723][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:53:43,224][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:53:43,725][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:53:44,228][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:53:44,730][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:53:45,232][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:53:45,734][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:53:46,236][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:53:46,737][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:53:47,238][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:53:47,739][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:53:48,240][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:53:48,741][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:53:49,242][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:53:49,743][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:53:50,244][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:53:50,745][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:53:51,247][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:53:51,748][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:53:52,249][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:53:52,751][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:53:53,252][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:53:53,754][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:53:54,255][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:53:54,757][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:53:55,258][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:53:55,760][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:53:56,260][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:53:56,763][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:53:57,266][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:53:57,769][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:53:58,272][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:53:58,774][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:53:59,277][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:53:59,779][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:54:00,282][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:54:00,783][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:54:01,286][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:54:01,789][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:54:02,292][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:54:02,796][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:54:03,298][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:54:03,800][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:54:04,303][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:54:04,805][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:54:05,308][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:54:05,810][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:54:06,312][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:54:06,814][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:54:07,316][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:54:07,817][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:54:08,318][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:54:08,822][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:54:09,324][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:54:09,826][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:54:10,329][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:54:10,831][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:54:11,335][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:54:11,838][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:54:12,341][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:54:12,842][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:54:13,343][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:54:13,844][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:54:14,347][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:54:14,848][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:54:15,349][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:54:15,851][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:54:16,352][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:54:16,853][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:54:17,356][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:54:17,857][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:54:18,358][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:54:18,860][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:54:19,360][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:54:19,862][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:54:20,364][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21746 tokens. [2026-03-25 19:54:20,981][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-25 19:54:21,714][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:54:21,717][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:54:21,718][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:54:22,350][__main__][INFO] - Iteration 192 took 1m 13s (8.34% Gen, 90.80% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 14m 7s. Estimated total time: 61h 33m 16s. Time estimates for 10 more iterations: 12m 18s, 100 more iterations: 2h 3m 6s, 500 more iterations: 10h 15m 32s. [2026-03-25 19:54:22,353][__main__][INFO] - Starting iteration 192. [2026-03-25 19:54:22,754][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:54:22,754][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:54:29,292][__main__][INFO] - Number of regex retries in iteration 192: 0 [2026-03-25 19:54:29,293][__main__][INFO] - agents played in iteration 192 are Bob, Alice [2026-03-25 19:54:30,191][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:54:30,766][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:54:31,222][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:54:31,725][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:54:32,222][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:54:32,719][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:54:33,217][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:54:33,714][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:54:34,212][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:54:34,709][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:54:35,211][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:54:35,713][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:54:36,214][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:54:36,715][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:54:37,217][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:54:37,719][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:54:38,222][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:54:38,722][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:54:39,225][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:54:39,727][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:54:40,230][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:54:40,732][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:54:41,236][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:54:41,739][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:54:42,240][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:54:42,742][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:54:43,243][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:54:43,744][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:54:44,246][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:54:44,747][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:54:45,247][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:54:45,749][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:54:46,250][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:54:46,751][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:54:47,251][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:54:47,752][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:54:48,252][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:54:48,753][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:54:49,254][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:54:49,755][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:54:50,255][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:54:50,756][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:54:51,257][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:54:51,758][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:54:52,259][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:54:52,760][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:54:53,262][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:54:53,764][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:54:54,265][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:54:54,766][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:54:55,266][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:54:55,769][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:54:56,270][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:54:56,771][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:54:57,272][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:54:57,772][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:54:58,273][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:54:58,773][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:54:59,274][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:54:59,774][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:55:00,275][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:55:00,776][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:55:01,276][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:55:01,776][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:55:02,276][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:55:02,777][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:55:03,276][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:55:03,773][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:55:04,270][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:55:04,767][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:55:05,265][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:55:05,763][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:55:06,259][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:55:06,755][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:55:07,258][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:55:07,760][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:55:08,261][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:55:08,763][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:55:09,263][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:55:09,764][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:55:10,265][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:55:10,767][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:55:11,271][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:55:11,775][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:55:12,276][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:55:12,778][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:55:13,279][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:55:13,781][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:55:14,283][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:55:14,785][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:55:15,287][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:55:15,791][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:55:16,292][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:55:16,793][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:55:17,295][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:55:17,796][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:55:18,297][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:55:18,798][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:55:19,299][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:55:19,801][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:55:20,301][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:55:20,813][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:55:21,315][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:55:21,816][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:55:22,318][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:55:22,820][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:55:23,322][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:55:23,824][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:55:24,328][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:55:24,831][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:55:25,334][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:55:25,836][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:55:26,338][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:55:26,840][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:55:27,341][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:55:27,843][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:55:28,344][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:55:28,846][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:55:29,348][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:55:29,848][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:55:30,350][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:55:30,852][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:55:31,353][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:55:31,854][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:55:32,355][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:55:32,855][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:55:33,357][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:55:33,857][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:55:34,358][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:55:34,858][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 19:55:35,479][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.25%, ΔTime: 00:01:04 [2026-03-25 19:55:36,210][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:55:36,213][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:55:36,214][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:55:36,856][__main__][INFO] - Iteration 193 took 1m 14s (8.82% Gen, 90.31% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 24m 46s. Estimated total time: 61h 45m 9s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 30s, 500 more iterations: 10h 17m 31s. [2026-03-25 19:55:36,859][__main__][INFO] - Starting iteration 193. [2026-03-25 19:55:37,259][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:55:37,260][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:55:40,096][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:55:40,651][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:55:44,064][__main__][INFO] - Number of regex retries in iteration 193: 2 [2026-03-25 19:55:44,065][__main__][INFO] - agents played in iteration 193 are Bob, Alice [2026-03-25 19:55:44,966][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:55:45,549][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:55:46,007][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:55:46,513][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:55:47,015][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:55:47,516][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:55:48,017][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:55:48,518][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:55:49,019][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:55:49,520][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:55:50,023][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:55:50,525][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:55:51,028][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:55:51,529][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:55:52,032][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:55:52,535][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:55:53,037][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:55:53,540][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:55:54,041][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:55:54,542][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:55:55,042][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:55:55,543][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:55:56,043][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:55:56,544][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:55:57,045][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:55:57,545][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:55:58,049][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:55:58,552][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:55:59,054][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:55:59,557][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:56:00,059][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:56:00,561][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:56:01,062][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:56:01,564][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:56:02,066][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:56:02,567][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:56:03,068][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:56:03,569][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:56:04,070][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:56:04,571][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:56:05,072][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:56:05,573][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:56:06,095][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:56:06,602][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:56:07,107][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:56:07,611][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:56:08,116][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:56:08,620][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:56:09,124][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:56:09,629][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:56:10,132][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:56:10,635][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:56:11,138][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:56:11,642][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:56:12,144][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:56:12,648][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:56:13,150][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:56:13,652][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:56:14,153][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:56:14,654][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:56:15,154][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:56:15,654][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:56:16,155][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:56:16,655][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:56:17,156][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:56:17,656][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:56:18,157][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:56:18,657][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:56:19,158][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:56:19,658][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:56:20,159][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:56:20,659][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:56:21,159][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:56:21,659][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:56:22,161][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:56:22,663][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:56:23,165][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:56:23,667][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:56:24,170][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:56:24,672][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:56:25,174][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:56:25,676][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:56:26,177][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:56:26,678][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:56:27,178][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:56:27,678][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:56:28,178][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:56:28,679][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:56:29,179][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:56:29,680][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:56:30,182][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:56:30,684][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:56:31,188][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:56:31,690][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:56:32,192][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:56:32,694][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:56:33,196][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:56:33,698][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:56:34,199][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:56:34,700][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:56:35,201][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:56:35,702][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:56:36,202][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:56:36,703][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:56:37,208][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:56:37,710][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:56:38,214][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:56:38,719][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:56:39,224][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:56:39,730][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:56:40,235][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:56:40,740][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:56:41,244][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:56:41,752][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:56:42,255][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:56:42,757][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:56:43,259][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:56:43,761][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:56:44,264][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:56:44,767][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:56:45,269][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:56:45,772][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:56:46,273][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:56:46,773][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:56:47,273][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:56:47,774][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:56:48,276][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:56:48,776][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:56:49,276][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:56:49,777][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 19:56:50,393][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:04 [2026-03-25 19:56:51,126][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:56:51,129][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:56:51,130][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:56:51,768][__main__][INFO] - Iteration 194 took 1m 14s (9.13% Gen, 90.01% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 43m 50s. Estimated total time: 62h 5m 29s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 10s, 500 more iterations: 10h 20m 54s. [2026-03-25 19:56:51,770][__main__][INFO] - Starting iteration 194. [2026-03-25 19:56:52,169][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:56:52,170][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:56:52,764][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:56:54,430][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:56:58,672][__main__][INFO] - Number of regex retries in iteration 194: 2 [2026-03-25 19:56:58,673][__main__][INFO] - agents played in iteration 194 are Bob, Alice [2026-03-25 19:56:59,581][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:57:00,431][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:57:00,888][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:57:01,394][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:57:01,895][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:57:02,397][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:57:02,897][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:57:03,399][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:57:03,899][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:57:04,399][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:57:04,903][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:57:05,410][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:57:05,914][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:57:06,418][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:57:06,922][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:57:07,426][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:57:07,931][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:57:08,435][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:57:08,936][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:57:09,436][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:57:09,937][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:57:10,437][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:57:10,937][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:57:11,439][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:57:11,940][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:57:12,441][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:57:12,941][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:57:13,442][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:57:13,941][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:57:14,441][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:57:14,942][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:57:15,443][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:57:15,944][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:57:16,445][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:57:16,944][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:57:17,446][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:57:17,949][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:57:18,449][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:57:18,949][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:57:19,449][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:57:19,949][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:57:20,450][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:57:20,984][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:57:21,469][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:57:21,968][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:57:22,468][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:57:22,968][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:57:23,468][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:57:23,969][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:57:24,469][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:57:24,970][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:57:25,471][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:57:25,972][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:57:26,473][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:57:26,974][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:57:27,474][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:57:27,975][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:57:28,476][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:57:28,976][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:57:29,476][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:57:29,977][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:57:30,478][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:57:30,979][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:57:31,480][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:57:31,980][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:57:32,480][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:57:32,979][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:57:33,479][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:57:33,979][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:57:34,480][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:57:34,980][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:57:35,481][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:57:35,980][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:57:36,479][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:57:36,982][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:57:37,485][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:57:37,988][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:57:38,491][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:57:38,995][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:57:39,497][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:57:40,000][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:57:40,503][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:57:41,005][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:57:41,508][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:57:42,009][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:57:42,510][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:57:43,010][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:57:43,510][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:57:44,010][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:57:44,510][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:57:45,012][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:57:45,513][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:57:46,013][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:57:46,515][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:57:47,016][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:57:47,517][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:57:48,017][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:57:48,518][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:57:49,020][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:57:49,520][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:57:50,022][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:57:50,523][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:57:51,024][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:57:51,524][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:57:52,024][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:57:52,525][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:57:53,023][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:57:53,523][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:57:54,022][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:57:54,522][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:57:55,020][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:57:55,519][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:57:56,018][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:57:56,517][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:57:57,018][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:57:57,518][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:57:58,019][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:57:58,520][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:57:59,021][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:57:59,521][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:58:00,022][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:58:00,523][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:58:01,024][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:58:01,525][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:58:02,025][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:58:02,528][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:58:03,029][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:58:03,530][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:58:04,031][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:58:04,532][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 19:58:05,154][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:04 [2026-03-25 19:58:05,888][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:58:05,890][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:58:05,891][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:58:06,534][__main__][INFO] - Iteration 195 took 1m 14s (8.74% Gen, 90.39% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 35m 24s. Estimated total time: 61h 58m 17s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 56s, 500 more iterations: 10h 19m 42s. [2026-03-25 19:58:06,537][__main__][INFO] - Starting iteration 195. [2026-03-25 19:58:06,936][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:58:06,937][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:58:13,467][__main__][INFO] - Number of regex retries in iteration 195: 0 [2026-03-25 19:58:13,468][__main__][INFO] - agents played in iteration 195 are Bob, Alice [2026-03-25 19:58:14,375][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:58:14,957][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:58:15,414][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:58:15,920][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:58:16,421][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:58:16,921][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:58:17,421][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:58:17,921][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:58:18,422][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:58:18,922][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:58:19,425][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:58:19,926][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:58:20,426][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:58:20,926][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:58:21,430][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:58:21,931][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:58:22,432][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:58:22,934][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:58:23,437][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:58:23,939][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:58:24,441][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:58:24,943][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:58:25,444][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:58:25,946][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:58:26,448][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:58:26,950][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:58:27,452][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:58:27,956][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:58:28,457][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:58:28,958][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:58:29,459][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:58:29,959][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:58:30,460][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:58:30,961][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:58:31,462][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:58:31,962][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:58:32,462][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:58:32,963][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:58:33,464][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:58:33,964][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:58:34,465][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:58:34,966][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:58:35,466][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:58:35,967][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:58:36,466][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:58:36,969][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:58:37,470][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:58:37,971][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:58:38,472][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:58:38,973][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:58:39,473][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:58:39,973][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:58:40,473][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:58:40,973][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:58:41,477][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:58:41,978][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:58:42,478][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:58:42,977][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:58:43,479][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 19:58:43,979][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 19:58:44,481][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 19:58:44,982][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 19:58:45,483][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 19:58:45,983][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 19:58:46,484][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 19:58:46,986][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 19:58:47,487][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 19:58:47,987][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 19:58:48,488][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 19:58:48,989][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 19:58:49,489][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 19:58:49,991][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 19:58:50,491][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 19:58:50,992][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 19:58:51,493][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 19:58:51,993][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 19:58:52,494][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 19:58:52,995][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 19:58:53,495][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 19:58:53,998][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 19:58:54,498][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 19:58:54,999][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 19:58:55,500][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 19:58:56,002][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 19:58:56,504][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 19:58:57,006][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 19:58:57,509][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 19:58:58,010][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 19:58:58,512][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 19:58:59,015][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 19:58:59,516][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 19:59:00,018][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 19:59:00,519][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 19:59:01,021][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 19:59:01,522][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 19:59:02,023][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 19:59:02,524][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 19:59:03,025][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 19:59:03,528][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 19:59:04,029][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 19:59:04,530][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 19:59:05,031][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 19:59:05,532][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 19:59:06,034][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 19:59:06,536][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 19:59:07,037][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 19:59:07,537][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 19:59:08,038][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 19:59:08,538][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 19:59:09,039][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 19:59:09,540][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 19:59:10,041][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 19:59:10,541][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 19:59:11,042][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 19:59:11,544][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 19:59:12,044][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 19:59:12,546][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 19:59:13,046][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 19:59:13,546][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 19:59:14,046][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 19:59:14,546][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 19:59:15,048][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 19:59:15,550][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 19:59:16,052][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 19:59:16,553][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 19:59:17,054][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 19:59:17,555][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 19:59:18,056][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 19:59:18,557][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 19:59:19,059][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21734 tokens. [2026-03-25 19:59:19,679][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 19:59:20,408][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 19:59:20,410][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 19:59:20,412][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 19:59:21,050][__main__][INFO] - Iteration 196 took 1m 14s (8.81% Gen, 90.33% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 21m 33s. Estimated total time: 61h 45m 41s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 31s, 500 more iterations: 10h 17m 36s. [2026-03-25 19:59:21,051][__main__][INFO] - Starting iteration 196. [2026-03-25 19:59:21,454][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 19:59:21,455][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 19:59:27,178][mllm.models.large_language_model_local][WARNING] - Response Proposals are strategic, and given the values, it's important to leverage the significant value I have for books while ensuring I secure a fair share of hats and balls as well. Let's allocate the items in a way that maximizes the points while considering the risk of over-claiming. - For hats, since we both value them at 1, sharing equally or nearly equally is a reasonable approach. - For books, given Alice's higher value for them, it might be risky to propose more than what I value, but it's still important to claim some to ensure a high value contribution. - For balls, as both of us value them the same, we can share them proportionally or similar to hats. Given these considerations, a balanced proposal might be: Proposal: 5 hats, 5 books, 5 balls This allows for a fair distribution of hats and balls while maximizing the potential points from books. did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 19:59:29,729][__main__][INFO] - Number of regex retries in iteration 196: 1 [2026-03-25 19:59:29,730][__main__][INFO] - agents played in iteration 196 are Bob, Alice [2026-03-25 19:59:30,627][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 19:59:31,208][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 19:59:31,664][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 19:59:32,168][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 19:59:32,668][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 19:59:33,169][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 19:59:33,671][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 19:59:34,171][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 19:59:34,671][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 19:59:35,171][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 19:59:35,674][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 19:59:36,175][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 19:59:36,676][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 19:59:37,179][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 19:59:37,681][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 19:59:38,182][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 19:59:38,683][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 19:59:39,184][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 19:59:39,686][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 19:59:40,188][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 19:59:40,689][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 19:59:41,193][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 19:59:41,696][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 19:59:42,199][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 19:59:42,700][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 19:59:43,201][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 19:59:43,705][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 19:59:44,207][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 19:59:44,711][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 19:59:45,213][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 19:59:45,716][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 19:59:46,219][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 19:59:46,721][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 19:59:47,223][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 19:59:47,721][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 19:59:48,219][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 19:59:48,719][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 19:59:49,218][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 19:59:49,717][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 19:59:50,217][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 19:59:50,716][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 19:59:51,215][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 19:59:51,716][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 19:59:52,216][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 19:59:52,717][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 19:59:53,218][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 19:59:53,718][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 19:59:54,219][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 19:59:54,718][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 19:59:55,218][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 19:59:55,720][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 19:59:56,221][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 19:59:56,722][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 19:59:57,223][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 19:59:57,724][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 19:59:58,225][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 19:59:58,726][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 19:59:59,229][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 19:59:59,729][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:00:00,230][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:00:00,729][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:00:01,229][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:00:01,730][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:00:02,231][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:00:02,731][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:00:03,231][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:00:03,732][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:00:04,232][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:00:04,733][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:00:05,233][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:00:05,734][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:00:06,234][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:00:06,735][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:00:07,236][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:00:07,738][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:00:08,239][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:00:08,740][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:00:09,242][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:00:09,743][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:00:10,245][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:00:10,746][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:00:11,249][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:00:11,752][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:00:12,254][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:00:12,755][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:00:13,257][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:00:13,757][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:00:14,259][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:00:14,760][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:00:15,261][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:00:15,763][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:00:16,265][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:00:16,767][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:00:17,269][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:00:17,771][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:00:18,273][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:00:18,775][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:00:19,277][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:00:19,776][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:00:20,274][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:00:20,773][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:00:21,273][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:00:21,772][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:00:22,271][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:00:22,770][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:00:23,269][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:00:23,770][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:00:24,270][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:00:24,770][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:00:25,270][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:00:25,770][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:00:26,270][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:00:26,771][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:00:27,271][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:00:27,771][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:00:28,272][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:00:28,773][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:00:29,274][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:00:29,775][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:00:30,276][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:00:30,777][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:00:31,278][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:00:31,778][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:00:32,278][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:00:32,778][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:00:33,278][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:00:33,778][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:00:34,277][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:00:34,777][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:00:35,277][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-25 20:00:35,892][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.15%, Current % of VRAM taken: 60.51%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-25 20:00:36,621][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:00:36,623][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:00:36,625][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:00:37,264][__main__][INFO] - Iteration 197 took 1m 15s (10.92% Gen, 88.24% Train). Generation: 8s, Training: 1m 6s. Estimated remaining time: 58h 45m 5s. Estimated total time: 63h 10m 29s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 20s, 500 more iterations: 10h 31m 44s. [2026-03-25 20:00:37,266][__main__][INFO] - Starting iteration 197. [2026-03-25 20:00:37,667][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 20:00:37,667][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:00:44,443][__main__][INFO] - Number of regex retries in iteration 197: 0 [2026-03-25 20:00:44,444][__main__][INFO] - agents played in iteration 197 are Bob, Alice [2026-03-25 20:00:45,346][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:00:45,926][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:00:46,385][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:00:46,891][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:00:47,393][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:00:47,895][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:00:48,397][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:00:48,898][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:00:49,399][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:00:49,900][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:00:50,404][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:00:50,907][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:00:51,409][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:00:51,912][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:00:52,414][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:00:52,917][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:00:53,419][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:00:53,921][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:00:54,422][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:00:54,922][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:00:55,423][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:00:55,924][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:00:56,424][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:00:56,926][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:00:57,426][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:00:57,926][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:00:58,424][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:00:58,923][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:00:59,422][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:00:59,921][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:01:00,421][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:01:00,920][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:01:01,420][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:01:01,920][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:01:02,422][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:01:02,924][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:01:03,427][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:01:03,929][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:01:04,431][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:01:04,933][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:01:05,435][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:01:05,938][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:01:06,442][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:01:06,946][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:01:07,452][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:01:07,956][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:01:08,459][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:01:08,963][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:01:09,465][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:01:09,967][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:01:10,468][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:01:10,971][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:01:11,474][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:01:11,975][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:01:12,476][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:01:12,977][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:01:13,477][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:01:13,978][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:01:14,478][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:01:14,979][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:01:15,480][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:01:15,981][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:01:16,481][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:01:16,981][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:01:17,482][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:01:17,982][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:01:18,484][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:01:18,985][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:01:19,488][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:01:19,990][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:01:20,492][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:01:20,993][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:01:21,495][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:01:21,997][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:01:22,499][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:01:23,001][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:01:23,505][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:01:24,008][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:01:24,510][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:01:25,012][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:01:25,514][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:01:26,016][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:01:26,517][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:01:27,018][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:01:27,518][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:01:28,019][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:01:28,519][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:01:29,019][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:01:29,520][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:01:30,020][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:01:30,519][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:01:31,019][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:01:31,518][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:01:32,017][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:01:32,517][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:01:33,016][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:01:33,516][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:01:34,015][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:01:34,517][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:01:35,020][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:01:35,521][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:01:36,024][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:01:36,526][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:01:37,029][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:01:37,531][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:01:38,034][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:01:38,536][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:01:39,038][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:01:39,541][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:01:40,043][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:01:40,545][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:01:41,048][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:01:41,552][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:01:42,055][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:01:42,557][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:01:43,058][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:01:43,561][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:01:44,062][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:01:44,563][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:01:45,064][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:01:45,565][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:01:46,066][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:01:46,566][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:01:47,067][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:01:47,569][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:01:48,070][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:01:48,571][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:01:49,072][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:01:49,573][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:01:50,074][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21747 tokens. [2026-03-25 20:01:50,693][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 20:01:51,420][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:01:51,422][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:01:51,424][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:01:52,061][__main__][INFO] - Iteration 198 took 1m 14s (9.11% Gen, 90.03% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 33m 7s. Estimated total time: 61h 59m 45s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 59s, 500 more iterations: 10h 19m 57s. [2026-03-25 20:01:52,063][__main__][INFO] - Starting iteration 198. [2026-03-25 20:01:52,463][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 20:01:52,464][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:01:58,701][__main__][INFO] - Number of regex retries in iteration 198: 0 [2026-03-25 20:01:58,702][__main__][INFO] - agents played in iteration 198 are Bob, Alice [2026-03-25 20:01:59,598][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:02:00,177][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:02:00,634][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:02:01,139][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:02:01,640][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:02:02,141][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:02:02,642][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:02:03,144][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:02:03,644][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:02:04,143][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:02:04,644][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:02:05,145][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:02:05,647][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:02:06,148][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:02:06,650][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:02:07,151][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:02:07,652][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:02:08,153][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:02:08,656][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:02:09,159][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:02:09,660][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:02:10,162][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:02:10,663][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:02:11,166][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:02:11,671][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:02:12,173][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:02:12,676][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:02:13,178][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:02:13,680][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:02:14,182][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:02:14,685][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:02:15,187][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:02:15,690][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:02:16,193][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:02:16,694][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:02:17,197][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:02:17,699][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:02:18,201][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:02:18,703][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:02:19,204][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:02:19,706][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:02:20,208][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:02:20,710][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:02:21,211][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:02:21,712][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:02:22,213][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:02:22,714][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:02:23,215][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:02:23,715][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:02:24,216][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:02:24,717][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:02:25,218][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:02:25,719][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:02:26,221][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:02:26,721][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:02:27,224][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:02:27,725][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:02:28,226][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:02:28,726][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:02:29,229][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:02:29,731][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:02:30,233][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:02:30,735][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:02:31,236][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:02:31,737][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:02:32,238][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:02:32,738][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:02:33,239][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:02:33,738][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:02:34,238][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:02:34,738][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:02:35,238][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:02:35,738][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:02:36,238][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:02:36,739][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:02:37,243][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:02:37,744][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:02:38,245][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:02:38,746][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:02:39,248][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:02:39,749][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:02:40,250][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:02:40,751][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:02:41,255][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:02:41,757][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:02:42,258][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:02:42,759][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:02:43,260][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:02:43,763][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:02:44,264][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:02:44,768][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:02:45,271][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:02:45,773][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:02:46,277][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:02:46,779][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:02:47,281][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:02:47,784][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:02:48,287][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:02:48,789][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:02:49,291][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:02:49,792][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:02:50,293][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:02:50,794][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:02:51,295][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:02:51,796][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:02:52,299][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:02:52,799][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:02:53,300][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:02:53,800][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:02:54,301][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:02:54,801][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:02:55,301][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:02:55,801][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:02:56,301][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:02:56,800][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:02:57,299][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:02:57,798][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:02:58,298][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:02:58,798][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:02:59,298][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:02:59,797][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:03:00,298][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:03:00,799][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:03:01,301][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:03:01,803][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:03:02,304][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:03:02,805][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:03:03,307][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:03:03,810][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:03:04,311][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21747 tokens. [2026-03-25 20:03:04,931][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 20:03:05,661][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:03:05,663][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:03:05,665][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:03:06,258][__main__][INFO] - Iteration 199 took 1m 13s (8.45% Gen, 90.74% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 1m 53s. Estimated total time: 61h 29m 46s. Time estimates for 10 more iterations: 12m 17s, 100 more iterations: 2h 2m 59s, 500 more iterations: 10h 14m 57s. [2026-03-25 20:03:06,260][__main__][INFO] - Starting iteration 199. [2026-03-25 20:03:06,661][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 20:03:06,661][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:03:12,929][__main__][INFO] - Number of regex retries in iteration 199: 0 [2026-03-25 20:03:12,930][__main__][INFO] - agents played in iteration 199 are Bob, Alice [2026-03-25 20:03:13,829][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:03:14,410][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:03:14,869][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:03:15,375][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:03:15,876][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:03:16,378][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:03:16,878][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:03:17,378][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:03:17,878][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:03:18,379][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:03:18,879][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:03:19,380][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:03:19,881][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:03:20,380][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:03:20,880][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:03:21,381][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:03:21,881][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:03:22,382][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:03:22,884][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:03:23,386][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:03:23,888][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:03:24,392][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:03:24,894][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:03:25,396][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:03:25,897][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:03:26,398][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:03:26,898][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:03:27,399][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:03:27,898][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:03:28,399][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:03:28,898][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:03:29,398][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:03:29,897][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:03:30,397][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:03:30,898][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:03:31,398][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:03:31,899][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:03:32,399][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:03:32,899][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:03:33,400][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:03:33,900][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:03:34,400][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:03:34,901][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:03:35,401][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:03:35,901][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:03:36,401][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:03:36,900][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:03:37,400][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:03:37,900][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:03:38,400][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:03:38,901][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:03:39,401][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:03:39,900][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:03:40,400][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:03:40,900][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:03:41,400][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:03:41,900][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:03:42,401][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:03:42,901][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:03:43,401][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:03:43,900][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:03:44,401][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:03:44,901][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:03:45,401][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:03:45,902][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:03:46,405][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:03:46,905][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:03:47,411][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:03:47,911][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:03:48,413][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:03:48,914][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:03:49,416][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:03:49,917][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:03:50,418][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:03:50,919][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:03:51,419][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:03:51,921][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:03:52,421][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:03:52,921][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:03:53,421][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:03:53,921][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:03:54,421][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:03:54,922][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:03:55,424][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:03:55,926][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:03:56,427][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:03:56,929][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:03:57,431][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:03:57,933][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:03:58,435][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:03:58,935][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:03:59,435][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:03:59,935][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:04:00,435][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:04:00,935][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:04:01,436][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:04:01,936][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:04:02,436][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:04:02,937][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:04:03,438][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:04:03,939][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:04:04,439][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:04:04,940][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:04:05,440][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:04:05,941][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:04:06,442][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:04:06,942][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:04:07,444][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:04:07,945][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:04:08,445][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:04:08,946][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:04:09,445][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:04:09,944][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:04:10,444][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:04:10,944][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:04:11,446][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:04:11,947][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:04:12,446][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:04:12,946][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:04:13,445][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:04:13,946][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:04:14,447][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:04:14,948][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:04:15,450][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:04:15,949][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:04:16,451][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:04:16,951][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:04:17,452][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:04:17,952][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:04:18,453][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21714 tokens. [2026-03-25 20:04:19,066][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-25 20:04:19,797][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:04:19,799][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:04:19,801][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:04:20,501][__main__][INFO] - Iteration 200 took 1m 13s (8.49% Gen, 90.56% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 2m 54s. Estimated total time: 61h 32m 1s. Time estimates for 10 more iterations: 12m 18s, 100 more iterations: 2h 3m 4s, 500 more iterations: 10h 15m 20s. [2026-03-25 20:04:20,508][__main__][INFO] - Starting iteration 200. [2026-03-25 20:04:20,907][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 3 and human policies 1. [2026-03-25 20:04:20,908][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:04:22,450][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:04:27,256][__main__][INFO] - Number of regex retries in iteration 200: 1 [2026-03-25 20:04:27,257][__main__][INFO] - agents played in iteration 200 are Bob, Alice [2026-03-25 20:04:28,157][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:04:28,741][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:04:29,198][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:04:29,703][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:04:30,204][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:04:30,706][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:04:31,207][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:04:31,709][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:04:32,210][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:04:32,713][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:04:33,213][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:04:33,714][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:04:34,214][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:04:34,715][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:04:35,216][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:04:35,718][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:04:36,218][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:04:36,719][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:04:37,222][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:04:37,724][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:04:38,225][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:04:38,728][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:04:39,231][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:04:39,733][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:04:40,235][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:04:40,737][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:04:41,239][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:04:41,741][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:04:42,241][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:04:42,742][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:04:43,243][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:04:43,744][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:04:44,244][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:04:44,744][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:04:45,246][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:04:45,747][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:04:46,248][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:04:46,749][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:04:47,252][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:04:47,753][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:04:48,256][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:04:48,757][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:04:49,258][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:04:49,758][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:04:50,258][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:04:50,758][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:04:51,258][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:04:51,758][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:04:52,258][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:04:52,758][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:04:53,260][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:04:53,760][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:04:54,260][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:04:54,761][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:04:55,261][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:04:55,761][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:04:56,262][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:04:56,762][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:04:57,263][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:04:57,762][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:04:58,263][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:04:58,763][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:04:59,263][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:04:59,764][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:05:00,264][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:05:00,764][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:05:01,264][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:05:01,764][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:05:02,263][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:05:02,763][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:05:03,263][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:05:03,762][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:05:04,262][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:05:04,762][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:05:05,261][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:05:05,760][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:05:06,259][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:05:06,758][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:05:07,257][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:05:07,756][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:05:08,255][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:05:08,754][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:05:09,255][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:05:09,756][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:05:10,258][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:05:10,760][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:05:11,262][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:05:11,765][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:05:12,267][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:05:12,769][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:05:13,270][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:05:13,771][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:05:14,272][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:05:14,773][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:05:15,273][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:05:15,774][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:05:16,275][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:05:16,776][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:05:17,276][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:05:17,777][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:05:18,277][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:05:18,778][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:05:19,278][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:05:19,778][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:05:20,279][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:05:20,780][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:05:21,279][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:05:21,778][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:05:22,278][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:05:22,779][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:05:23,279][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:05:23,779][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:05:24,278][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:05:24,778][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:05:25,279][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:05:25,779][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:05:26,280][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:05:26,781][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:05:27,282][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:05:27,782][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:05:28,284][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:05:28,785][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:05:29,286][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:05:29,788][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:05:30,289][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:05:30,790][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:05:31,291][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:05:31,791][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:05:32,292][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:05:32,793][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 20:05:33,411][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-25 20:05:34,144][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:05:34,146][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:05:34,148][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:05:45,759][__main__][INFO] - Iteration 201 took 1m 24s (7.48% Gen, 78.83% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 66h 12m 5s. Estimated total time: 70h 42m 37s. Time estimates for 10 more iterations: 14m 8s, 100 more iterations: 2h 21m 25s, 500 more iterations: 11h 47m 6s. [2026-03-25 20:05:45,761][__main__][INFO] - Starting iteration 201. [2026-03-25 20:05:46,161][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:05:46,162][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:05:52,993][__main__][INFO] - Number of regex retries in iteration 201: 0 [2026-03-25 20:05:52,994][__main__][INFO] - agents played in iteration 201 are Bob, Alice [2026-03-25 20:05:53,896][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:05:54,481][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:05:54,942][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:05:55,450][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:05:55,954][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:05:56,456][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:05:56,957][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:05:57,459][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:05:57,961][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:05:58,464][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:05:58,965][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:05:59,467][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:05:59,968][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:06:00,469][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:06:00,971][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:06:01,472][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:06:01,974][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:06:02,475][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:06:02,975][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:06:03,475][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:06:03,975][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:06:04,475][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:06:04,975][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:06:05,474][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:06:05,974][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:06:06,474][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:06:06,974][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:06:07,473][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:06:07,973][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:06:08,473][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:06:08,973][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:06:09,474][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:06:09,973][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:06:10,473][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:06:10,974][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:06:11,476][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:06:11,977][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:06:12,477][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:06:12,977][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:06:13,478][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:06:13,978][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:06:14,477][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:06:14,978][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:06:15,479][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:06:15,979][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:06:16,480][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:06:16,981][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:06:17,481][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:06:17,981][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:06:18,481][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:06:18,981][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:06:19,481][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:06:19,981][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:06:20,482][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:06:20,981][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:06:21,480][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:06:21,980][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:06:22,480][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:06:22,980][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:06:23,480][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:06:23,980][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:06:24,479][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:06:24,979][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:06:25,478][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:06:25,978][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:06:26,478][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:06:26,979][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:06:27,482][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:06:27,982][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:06:28,485][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:06:28,987][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:06:29,490][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:06:29,991][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:06:30,493][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:06:30,993][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:06:31,494][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:06:31,995][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:06:32,496][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:06:32,997][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:06:33,498][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:06:33,998][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:06:34,500][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:06:35,000][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:06:35,500][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:06:36,001][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:06:36,501][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:06:37,001][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:06:37,501][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:06:38,000][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:06:38,500][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:06:39,000][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:06:39,501][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:06:40,000][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:06:40,500][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:06:41,000][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:06:41,502][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:06:42,001][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:06:42,501][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:06:43,001][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:06:43,501][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:06:44,001][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:06:44,501][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:06:45,000][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:06:45,500][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:06:46,001][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:06:46,501][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:06:47,002][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:06:47,502][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:06:48,003][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:06:48,504][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:06:49,005][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:06:49,508][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:06:50,010][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:06:50,511][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:06:51,014][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:06:51,516][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:06:52,017][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:06:52,519][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:06:53,020][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:06:53,521][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:06:54,021][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:06:54,521][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:06:55,020][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:06:55,521][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:06:56,022][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:06:56,522][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:06:57,022][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:06:57,523][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:06:58,023][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:06:58,524][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21737 tokens. [2026-03-25 20:06:59,139][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 20:06:59,874][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:06:59,877][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:06:59,878][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:07:00,516][__main__][INFO] - Iteration 202 took 1m 14s (9.19% Gen, 89.95% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 25m 58s. Estimated total time: 61h 57m 45s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 55s, 500 more iterations: 10h 19m 37s. [2026-03-25 20:07:00,518][__main__][INFO] - Starting iteration 202. [2026-03-25 20:07:00,916][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:07:00,916][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:07:01,500][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:07:03,828][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:07:07,812][__main__][INFO] - Number of regex retries in iteration 202: 2 [2026-03-25 20:07:07,813][__main__][INFO] - agents played in iteration 202 are Bob, Alice [2026-03-25 20:07:08,717][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:07:09,300][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:07:09,757][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:07:10,263][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:07:10,765][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:07:11,268][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:07:11,770][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:07:12,272][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:07:12,774][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:07:13,276][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:07:13,780][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:07:14,282][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:07:14,784][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:07:15,286][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:07:15,788][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:07:16,290][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:07:16,793][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:07:17,296][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:07:17,797][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:07:18,298][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:07:18,797][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:07:19,297][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:07:19,798][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:07:20,298][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:07:20,799][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:07:21,300][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:07:21,801][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:07:22,301][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:07:22,801][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:07:23,303][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:07:23,804][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:07:24,305][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:07:24,806][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:07:25,307][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:07:25,811][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:07:26,314][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:07:26,817][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:07:27,319][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:07:27,822][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:07:28,324][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:07:28,827][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:07:29,331][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:07:29,833][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:07:30,334][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:07:30,836][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:07:31,338][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:07:31,839][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:07:32,341][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:07:32,842][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:07:33,344][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:07:33,846][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:07:34,347][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:07:34,851][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:07:35,354][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:07:35,857][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:07:36,360][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:07:36,861][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:07:37,363][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:07:37,864][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:07:38,366][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:07:38,868][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:07:39,371][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:07:39,873][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:07:40,375][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:07:40,878][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:07:41,383][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:07:41,884][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:07:42,386][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:07:42,888][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:07:43,392][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:07:43,894][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:07:44,396][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:07:44,899][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:07:45,399][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:07:45,901][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:07:46,404][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:07:46,907][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:07:47,409][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:07:47,912][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:07:48,414][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:07:48,916][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:07:49,419][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:07:49,921][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:07:50,423][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:07:50,925][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:07:51,426][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:07:51,929][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:07:52,432][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:07:52,934][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:07:53,435][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:07:53,936][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:07:54,438][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:07:54,939][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:07:55,441][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:07:55,942][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:07:56,444][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:07:56,945][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:07:57,446][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:07:57,951][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:07:58,453][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:07:58,956][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:07:59,459][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:07:59,960][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:08:00,462][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:08:00,960][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:08:01,462][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:08:01,964][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:08:02,465][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:08:02,966][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:08:03,467][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:08:03,969][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:08:04,474][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:08:04,979][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:08:05,483][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:08:05,987][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:08:06,495][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:08:06,998][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:08:07,501][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:08:08,003][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:08:08,506][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:08:09,011][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:08:09,514][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:08:10,016][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:08:10,518][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:08:11,020][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:08:11,524][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:08:12,028][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:08:12,531][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:08:13,033][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:08:13,536][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21724 tokens. [2026-03-25 20:08:14,160][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-25 20:08:14,889][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:08:14,891][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:08:14,893][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:08:15,532][__main__][INFO] - Iteration 203 took 1m 14s (9.24% Gen, 89.90% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 37m 47s. Estimated total time: 62h 10m 50s. Time estimates for 10 more iterations: 12m 26s, 100 more iterations: 2h 4m 21s, 500 more iterations: 10h 21m 48s. [2026-03-25 20:08:15,534][__main__][INFO] - Starting iteration 203. [2026-03-25 20:08:15,934][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:08:15,935][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:08:18,726][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:08:22,591][__main__][INFO] - Number of regex retries in iteration 203: 1 [2026-03-25 20:08:22,592][__main__][INFO] - agents played in iteration 203 are Bob, Alice [2026-03-25 20:08:23,501][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:08:24,112][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:08:24,574][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:08:25,083][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:08:25,586][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:08:26,094][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:08:26,603][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:08:27,111][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:08:27,616][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:08:28,119][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:08:28,620][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:08:29,123][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:08:29,624][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:08:30,126][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:08:30,627][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:08:31,129][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:08:31,630][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:08:32,131][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:08:32,634][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:08:33,137][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:08:33,639][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:08:34,140][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:08:34,642][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:08:35,143][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:08:35,645][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:08:36,146][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:08:36,646][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:08:37,149][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:08:37,652][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:08:38,153][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:08:38,654][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:08:39,155][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:08:39,655][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:08:40,156][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:08:40,654][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:08:41,154][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:08:41,656][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:08:42,155][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:08:42,653][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:08:43,152][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:08:43,651][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:08:44,152][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:08:44,657][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:08:45,160][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:08:45,663][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:08:46,165][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:08:46,667][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:08:47,170][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:08:47,673][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:08:48,175][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:08:48,675][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:08:49,175][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:08:49,675][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:08:50,175][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:08:50,675][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:08:51,175][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:08:51,674][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:08:52,174][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:08:52,676][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:08:53,176][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:08:53,676][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:08:54,178][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:08:54,678][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:08:55,178][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:08:55,678][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:08:56,178][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:08:56,678][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:08:57,179][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:08:57,680][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:08:58,181][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:08:58,682][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:08:59,182][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:08:59,683][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:09:00,185][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:09:00,684][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:09:01,184][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:09:01,684][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:09:02,183][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:09:02,682][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:09:03,181][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:09:03,681][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:09:04,180][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:09:04,681][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:09:05,181][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:09:05,682][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:09:06,182][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:09:06,682][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:09:07,183][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:09:07,684][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:09:08,185][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:09:08,686][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:09:09,187][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:09:09,689][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:09:10,190][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:09:10,691][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:09:11,192][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:09:11,692][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:09:12,194][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:09:12,692][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:09:13,191][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:09:13,692][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:09:14,191][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:09:14,690][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:09:15,188][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:09:15,686][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:09:16,184][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:09:16,686][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:09:17,189][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:09:17,691][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:09:18,192][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:09:18,693][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:09:19,195][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:09:19,697][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:09:20,198][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:09:20,697][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:09:21,197][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:09:21,695][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:09:22,194][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:09:22,693][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:09:23,193][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:09:23,692][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:09:24,191][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:09:24,692][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:09:25,191][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:09:25,692][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:09:26,194][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:09:26,707][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:09:27,211][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:09:27,715][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:09:28,217][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 20:09:28,846][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 20:09:29,583][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:09:29,585][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:09:29,586][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:09:30,270][__main__][INFO] - Iteration 204 took 1m 14s (8.96% Gen, 90.12% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 22m 30s. Estimated total time: 61h 56m 47s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 53s, 500 more iterations: 10h 19m 27s. [2026-03-25 20:09:30,272][__main__][INFO] - Starting iteration 204. [2026-03-25 20:09:30,672][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:09:30,673][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:09:33,437][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:09:37,174][__main__][INFO] - Number of regex retries in iteration 204: 1 [2026-03-25 20:09:37,175][__main__][INFO] - agents played in iteration 204 are Bob, Alice [2026-03-25 20:09:38,088][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:09:38,669][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:09:39,126][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:09:39,631][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:09:40,131][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:09:40,633][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:09:41,140][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:09:41,651][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:09:42,155][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:09:42,658][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:09:43,162][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:09:43,665][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:09:44,168][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:09:44,671][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:09:45,172][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:09:45,674][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:09:46,177][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:09:46,679][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:09:47,181][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:09:47,683][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:09:48,186][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:09:48,698][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:09:49,210][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:09:49,715][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:09:50,218][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:09:50,722][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:09:51,226][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:09:51,730][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:09:52,232][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:09:52,736][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:09:53,239][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:09:53,741][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:09:54,245][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:09:54,748][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:09:55,250][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:09:55,754][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:09:56,256][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:09:56,757][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:09:57,258][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:09:57,760][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:09:58,261][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:09:58,761][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:09:59,265][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:09:59,776][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:10:00,280][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:10:00,787][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:10:01,293][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:10:01,797][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:10:02,300][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:10:02,803][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:10:03,308][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:10:03,813][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:10:04,316][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:10:04,819][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:10:05,322][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:10:05,825][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:10:06,328][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:10:06,832][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:10:07,336][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:10:07,839][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:10:08,340][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:10:08,842][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:10:09,343][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:10:09,844][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:10:10,345][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:10:10,847][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:10:11,351][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:10:11,858][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:10:12,361][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:10:12,868][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:10:13,371][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:10:13,872][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:10:14,376][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:10:14,878][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:10:15,381][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:10:15,883][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:10:16,386][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:10:16,888][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:10:17,393][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:10:17,895][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:10:18,397][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:10:18,899][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:10:19,400][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:10:19,902][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:10:20,403][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:10:20,905][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:10:21,407][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:10:21,909][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:10:22,412][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:10:22,914][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:10:23,416][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:10:23,919][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:10:24,421][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:10:24,922][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:10:25,423][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:10:25,925][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:10:26,427][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:10:26,929][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:10:27,430][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:10:27,931][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:10:28,431][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:10:28,932][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:10:29,433][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:10:29,935][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:10:30,436][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:10:30,939][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:10:31,441][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:10:31,949][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:10:32,453][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:10:32,957][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:10:33,463][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:10:33,966][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:10:34,470][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:10:34,973][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:10:35,476][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:10:35,979][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:10:36,482][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:10:36,985][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:10:37,490][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:10:37,993][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:10:38,496][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:10:38,999][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:10:39,500][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:10:40,002][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:10:40,503][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:10:41,005][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:10:41,508][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:10:42,010][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:10:42,512][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:10:43,013][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 20:10:43,646][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 20:10:44,376][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:10:44,378][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:10:44,380][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:10:45,075][__main__][INFO] - Iteration 205 took 1m 14s (8.74% Gen, 90.32% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 24m 38s. Estimated total time: 62h 0m 10s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 0s, 500 more iterations: 10h 20m 1s. [2026-03-25 20:10:45,077][__main__][INFO] - Starting iteration 205. [2026-03-25 20:10:45,477][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:10:45,477][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:10:49,271][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:10:51,963][__main__][INFO] - Number of regex retries in iteration 205: 1 [2026-03-25 20:10:51,963][__main__][INFO] - agents played in iteration 205 are Bob, Alice [2026-03-25 20:10:52,881][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:10:53,464][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:10:53,922][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:10:54,429][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:10:54,930][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:10:55,433][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:10:55,935][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:10:56,436][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:10:56,936][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:10:57,438][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:10:57,935][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:10:58,432][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:10:58,929][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:10:59,426][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:10:59,922][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:11:00,419][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:11:00,916][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:11:01,412][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:11:01,915][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:11:02,416][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:11:02,917][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:11:03,418][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:11:03,919][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:11:04,419][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:11:04,920][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:11:05,421][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:11:05,922][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:11:06,422][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:11:06,922][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:11:07,422][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:11:07,922][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:11:08,422][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:11:08,922][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:11:09,421][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:11:09,921][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:11:10,420][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:11:10,919][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:11:11,421][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:11:11,920][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:11:12,420][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:11:12,919][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:11:13,419][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:11:13,918][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:11:14,418][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:11:14,917][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:11:15,418][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:11:15,919][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:11:16,421][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:11:16,921][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:11:17,421][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:11:17,928][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:11:18,431][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:11:18,932][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:11:19,434][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:11:19,939][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:11:20,440][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:11:20,940][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:11:21,441][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:11:21,942][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:11:22,444][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:11:22,946][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:11:23,448][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:11:23,949][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:11:24,451][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:11:24,953][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:11:25,454][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:11:25,955][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:11:26,456][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:11:26,957][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:11:27,458][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:11:27,958][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:11:28,459][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:11:28,959][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:11:29,459][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:11:29,956][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:11:30,453][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:11:30,950][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:11:31,449][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:11:31,947][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:11:32,444][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:11:32,941][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:11:33,438][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:11:33,938][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:11:34,439][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:11:34,940][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:11:35,441][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:11:35,942][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:11:36,443][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:11:36,945][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:11:37,449][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:11:37,951][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:11:38,451][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:11:38,952][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:11:39,454][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:11:39,955][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:11:40,457][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:11:40,958][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:11:41,461][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:11:41,961][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:11:42,471][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:11:42,974][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:11:43,476][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:11:43,979][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:11:44,486][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:11:44,988][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:11:45,490][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:11:45,993][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:11:46,494][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:11:46,997][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:11:47,499][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:11:48,000][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:11:48,501][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:11:49,001][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:11:49,502][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:11:50,002][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:11:50,502][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:11:51,002][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:11:51,502][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:11:52,003][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:11:52,502][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:11:53,001][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:11:53,501][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:11:54,002][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:11:54,504][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:11:55,005][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:11:55,505][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:11:56,007][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:11:56,511][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:11:57,015][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:11:57,518][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21746 tokens. [2026-03-25 20:11:58,154][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.23%, ΔTime: 00:01:04 [2026-03-25 20:11:58,884][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:11:58,886][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:11:58,888][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:11:59,590][__main__][INFO] - Iteration 206 took 1m 14s (8.75% Gen, 90.30% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 8m 55s. Estimated total time: 61h 45m 41s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 31s, 500 more iterations: 10h 17m 36s. [2026-03-25 20:11:59,593][__main__][INFO] - Starting iteration 206. [2026-03-25 20:11:59,991][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:11:59,991][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:12:04,088][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:12:05,848][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:12:06,859][__main__][INFO] - Number of regex retries in iteration 206: 2 [2026-03-25 20:12:06,859][__main__][INFO] - agents played in iteration 206 are Bob, Alice [2026-03-25 20:12:07,758][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:12:08,339][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:12:08,796][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:12:09,302][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:12:09,804][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:12:10,306][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:12:10,808][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:12:11,312][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:12:11,814][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:12:12,317][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:12:12,817][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:12:13,318][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:12:13,819][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:12:14,319][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:12:14,820][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:12:15,320][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:12:15,820][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:12:16,320][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:12:16,822][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:12:17,322][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:12:17,824][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:12:18,325][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:12:18,825][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:12:19,326][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:12:19,827][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:12:20,329][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:12:20,830][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:12:21,330][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:12:21,831][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:12:22,331][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:12:22,832][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:12:23,333][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:12:23,834][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:12:24,335][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:12:24,838][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:12:25,339][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:12:25,840][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:12:26,341][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:12:26,843][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:12:27,344][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:12:27,845][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:12:28,346][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:12:28,849][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:12:29,351][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:12:29,851][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:12:30,351][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:12:30,851][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:12:31,352][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:12:31,852][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:12:32,353][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:12:32,852][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:12:33,353][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:12:33,852][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:12:34,352][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:12:34,852][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:12:35,352][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:12:35,851][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:12:36,351][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:12:36,852][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:12:37,353][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:12:37,854][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:12:38,354][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:12:38,856][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:12:39,356][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:12:39,857][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:12:40,358][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:12:40,859][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:12:41,364][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:12:41,867][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:12:42,370][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:12:42,872][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:12:43,375][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:12:43,877][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:12:44,379][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:12:44,879][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:12:45,379][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:12:45,879][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:12:46,386][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:12:46,889][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:12:47,391][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:12:47,894][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:12:48,396][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:12:48,898][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:12:49,409][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:12:49,913][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:12:50,415][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:12:50,918][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:12:51,421][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:12:51,923][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:12:52,425][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:12:52,927][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:12:53,430][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:12:53,931][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:12:54,432][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:12:54,932][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:12:55,434][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:12:55,936][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:12:56,437][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:12:56,938][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:12:57,441][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:12:57,943][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:12:58,444][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:12:58,945][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:12:59,447][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:12:59,948][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:13:00,450][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:13:00,950][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:13:01,452][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:13:01,954][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:13:02,456][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:13:02,958][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:13:03,459][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:13:03,961][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:13:04,463][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:13:04,963][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:13:05,464][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:13:05,965][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:13:06,465][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:13:06,968][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:13:07,471][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:13:07,971][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:13:08,473][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:13:08,974][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:13:09,476][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:13:09,977][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:13:10,478][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:13:10,979][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:13:11,482][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:13:11,984][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:13:12,486][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 20:13:13,112][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 20:13:13,840][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:13:13,842][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:13:13,844][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:13:14,681][__main__][INFO] - Iteration 207 took 1m 14s (9.19% Gen, 89.68% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 36m 31s. Estimated total time: 62h 14m 32s. Time estimates for 10 more iterations: 12m 26s, 100 more iterations: 2h 4m 29s, 500 more iterations: 10h 22m 25s. [2026-03-25 20:13:14,683][__main__][INFO] - Starting iteration 207. [2026-03-25 20:13:15,081][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:13:15,081][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:13:17,448][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:13:21,960][__main__][INFO] - Number of regex retries in iteration 207: 1 [2026-03-25 20:13:21,960][__main__][INFO] - agents played in iteration 207 are Bob, Alice [2026-03-25 20:13:22,861][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:13:23,449][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:13:23,909][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:13:24,416][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:13:24,918][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:13:25,419][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:13:25,920][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:13:26,422][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:13:26,923][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:13:27,424][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:13:27,927][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:13:28,431][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:13:28,934][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:13:29,436][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:13:29,938][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:13:30,439][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:13:30,940][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:13:31,442][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:13:31,943][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:13:32,444][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:13:32,945][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:13:33,445][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:13:33,945][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:13:34,448][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:13:34,949][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:13:35,451][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:13:35,954][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:13:36,457][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:13:36,959][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:13:37,462][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:13:37,965][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:13:38,467][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:13:38,969][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:13:39,472][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:13:39,973][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:13:40,473][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:13:40,973][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:13:41,476][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:13:41,977][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:13:42,476][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:13:42,976][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:13:43,475][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:13:43,976][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:13:44,477][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:13:44,978][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:13:45,479][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:13:45,980][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:13:46,481][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:13:46,982][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:13:47,483][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:13:47,984][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:13:48,484][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:13:48,985][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:13:49,488][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:13:49,990][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:13:50,491][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:13:50,992][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:13:51,493][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:13:51,994][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:13:52,494][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:13:52,993][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:13:53,493][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:13:53,993][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:13:54,493][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:13:54,993][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:13:55,494][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:13:55,994][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:13:56,496][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:13:56,998][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:13:57,499][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:13:58,000][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:13:58,501][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:13:59,004][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:13:59,505][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:14:00,009][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:14:00,511][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:14:01,013][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:14:01,515][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:14:02,016][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:14:02,518][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:14:03,020][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:14:03,522][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:14:04,023][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:14:04,524][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:14:05,025][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:14:05,527][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:14:06,029][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:14:06,530][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:14:07,031][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:14:07,533][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:14:08,037][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:14:08,539][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:14:09,042][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:14:09,545][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:14:10,047][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:14:10,548][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:14:11,051][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:14:11,555][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:14:12,055][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:14:12,556][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:14:13,057][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:14:13,557][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:14:14,058][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:14:14,558][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:14:15,059][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:14:15,559][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:14:16,060][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:14:16,561][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:14:17,071][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:14:17,574][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:14:18,076][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:14:18,579][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:14:19,081][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:14:19,583][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:14:20,087][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:14:20,590][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:14:21,093][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:14:21,595][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:14:22,097][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:14:22,599][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:14:23,100][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:14:23,602][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:14:24,103][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:14:24,603][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:14:25,104][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:14:25,606][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:14:26,109][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:14:26,611][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:14:27,112][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:14:27,613][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-25 20:14:28,248][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 20:14:28,978][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:14:28,980][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:14:28,982][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:14:29,673][__main__][INFO] - Iteration 208 took 1m 14s (9.22% Gen, 89.85% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 30m 23s. Estimated total time: 62h 9m 39s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 19s, 500 more iterations: 10h 21m 36s. [2026-03-25 20:14:29,675][__main__][INFO] - Starting iteration 208. [2026-03-25 20:14:30,075][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:14:30,076][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:14:36,283][__main__][INFO] - Number of regex retries in iteration 208: 0 [2026-03-25 20:14:36,284][__main__][INFO] - agents played in iteration 208 are Bob, Alice [2026-03-25 20:14:37,194][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:14:37,776][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:14:38,233][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:14:38,739][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:14:39,241][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:14:39,741][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:14:40,241][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:14:40,741][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:14:41,244][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:14:41,747][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:14:42,249][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:14:42,750][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:14:43,251][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:14:43,752][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:14:44,253][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:14:44,754][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:14:45,255][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:14:45,756][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:14:46,257][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:14:46,759][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:14:47,260][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:14:47,760][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:14:48,262][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:14:48,762][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:14:49,262][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:14:49,762][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:14:50,262][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:14:50,762][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:14:51,263][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:14:51,763][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:14:52,263][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:14:52,762][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:14:53,262][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:14:53,762][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:14:54,262][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:14:54,764][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:14:55,264][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:14:55,764][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:14:56,265][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:14:56,765][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:14:57,266][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:14:57,767][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:14:58,269][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:14:58,770][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:14:59,272][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:14:59,774][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:15:00,277][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:15:00,779][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:15:01,281][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:15:01,781][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:15:02,280][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:15:02,781][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:15:03,282][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:15:03,782][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:15:04,283][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:15:04,784][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:15:05,284][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:15:05,785][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:15:06,286][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:15:06,786][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:15:07,286][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:15:07,786][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:15:08,287][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:15:08,787][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:15:09,290][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:15:09,791][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:15:10,291][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:15:10,792][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:15:11,295][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:15:11,797][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:15:12,297][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:15:12,797][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:15:13,298][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:15:13,798][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:15:14,300][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:15:14,801][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:15:15,302][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:15:15,805][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:15:16,309][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:15:16,812][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:15:17,315][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:15:17,817][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:15:18,320][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:15:18,822][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:15:19,326][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:15:19,828][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:15:20,330][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:15:20,833][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:15:21,335][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:15:21,838][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:15:22,340][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:15:22,842][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:15:23,343][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:15:23,846][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:15:24,349][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:15:24,851][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:15:25,353][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:15:25,854][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:15:26,356][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:15:26,857][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:15:27,357][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:15:27,859][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:15:28,359][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:15:28,861][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:15:29,361][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:15:29,862][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:15:30,363][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:15:30,865][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:15:31,366][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:15:31,868][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:15:32,369][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:15:32,871][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:15:33,373][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:15:33,874][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:15:34,376][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:15:34,878][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:15:35,379][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:15:35,879][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:15:36,381][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:15:36,882][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:15:37,384][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:15:37,885][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:15:38,386][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:15:38,886][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:15:39,389][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:15:39,891][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:15:40,392][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:15:40,893][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:15:41,397][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:15:41,898][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 20:15:42,534][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 20:15:43,265][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:15:43,267][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:15:43,269][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:15:43,977][__main__][INFO] - Iteration 209 took 1m 13s (8.40% Gen, 90.64% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 56h 54m 35s. Estimated total time: 61h 35m 6s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 10s, 500 more iterations: 10h 15m 51s. [2026-03-25 20:15:43,979][__main__][INFO] - Starting iteration 209. [2026-03-25 20:15:44,380][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:15:44,380][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:15:51,139][__main__][INFO] - Number of regex retries in iteration 209: 0 [2026-03-25 20:15:51,140][__main__][INFO] - agents played in iteration 209 are Bob, Alice [2026-03-25 20:15:52,050][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:15:52,631][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:15:53,089][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:15:53,594][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:15:54,095][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:15:54,596][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:15:55,097][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:15:55,598][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:15:56,098][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:15:56,599][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:15:57,102][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:15:57,603][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:15:58,105][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:15:58,607][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:15:59,109][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:15:59,611][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:16:00,114][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:16:00,618][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:16:01,120][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:16:01,620][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:16:02,122][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:16:02,623][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:16:03,123][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:16:03,625][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:16:04,128][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:16:04,628][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:16:05,132][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:16:05,635][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:16:06,138][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:16:06,640][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:16:07,145][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:16:07,648][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:16:08,151][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:16:08,654][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:16:09,156][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:16:09,657][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:16:10,157][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:16:10,658][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:16:11,160][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:16:11,663][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:16:12,165][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:16:12,666][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:16:13,166][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:16:13,667][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:16:14,167][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:16:14,670][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:16:15,171][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:16:15,672][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:16:16,173][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:16:16,674][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:16:17,175][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:16:17,677][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:16:18,179][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:16:18,680][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:16:19,182][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:16:19,682][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:16:20,184][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:16:20,686][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:16:21,186][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:16:21,687][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:16:22,188][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:16:22,688][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:16:23,189][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:16:23,690][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:16:24,191][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:16:24,692][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:16:25,193][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:16:25,694][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:16:26,195][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:16:26,696][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:16:27,196][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:16:27,698][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:16:28,199][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:16:28,700][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:16:29,201][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:16:29,702][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:16:30,203][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:16:30,705][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:16:31,207][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:16:31,710][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:16:32,212][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:16:32,714][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:16:33,216][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:16:33,717][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:16:34,219][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:16:34,720][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:16:35,222][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:16:35,722][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:16:36,223][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:16:36,724][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:16:37,227][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:16:37,730][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:16:38,232][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:16:38,734][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:16:39,237][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:16:39,740][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:16:40,243][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:16:40,745][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:16:41,248][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:16:41,751][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:16:42,252][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:16:42,754][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:16:43,255][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:16:43,756][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:16:44,257][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:16:44,758][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:16:45,259][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:16:45,759][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:16:46,260][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:16:46,761][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:16:47,262][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:16:47,762][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:16:48,262][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:16:48,762][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:16:49,263][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:16:49,763][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:16:50,264][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:16:50,765][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:16:51,265][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:16:51,766][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:16:52,268][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:16:52,769][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:16:53,269][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:16:53,771][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:16:54,272][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:16:54,774][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:16:55,280][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:16:55,783][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:16:56,284][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:16:56,785][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-25 20:16:57,416][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:04 [2026-03-25 20:16:58,151][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:16:58,153][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:16:58,154][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:16:58,988][__main__][INFO] - Iteration 210 took 1m 14s (9.06% Gen, 89.82% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 28m 41s. Estimated total time: 62h 10m 26s. Time estimates for 10 more iterations: 12m 26s, 100 more iterations: 2h 4m 20s, 500 more iterations: 10h 21m 44s. [2026-03-25 20:16:58,991][__main__][INFO] - Starting iteration 210. [2026-03-25 20:16:59,391][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:16:59,392][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:17:05,966][__main__][INFO] - Number of regex retries in iteration 210: 0 [2026-03-25 20:17:05,967][__main__][INFO] - agents played in iteration 210 are Bob, Alice [2026-03-25 20:17:06,976][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:17:07,556][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:17:08,016][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:17:08,523][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:17:09,025][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:17:09,526][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:17:10,029][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:17:10,565][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:17:11,067][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:17:11,569][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:17:12,070][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:17:12,571][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:17:13,073][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:17:13,574][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:17:14,075][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:17:14,576][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:17:15,076][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:17:15,578][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:17:16,079][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:17:16,579][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:17:17,080][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:17:17,581][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:17:18,080][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:17:18,581][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:17:19,084][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:17:19,585][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:17:20,084][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:17:20,584][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:17:21,083][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:17:21,582][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:17:22,081][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:17:22,581][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:17:23,081][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:17:23,580][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:17:24,084][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:17:24,587][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:17:25,093][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:17:25,595][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:17:26,098][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:17:26,601][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:17:27,102][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:17:27,605][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:17:28,109][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:17:28,612][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:17:29,115][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:17:29,617][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:17:30,120][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:17:30,623][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:17:31,125][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:17:31,628][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:17:32,129][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:17:32,630][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:17:33,131][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:17:33,633][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:17:34,134][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:17:34,636][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:17:35,137][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:17:35,639][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:17:36,141][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:17:36,645][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:17:37,152][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:17:37,655][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:17:38,157][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:17:38,660][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:17:39,162][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:17:39,665][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:17:40,166][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:17:40,668][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:17:41,169][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:17:41,672][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:17:42,173][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:17:42,675][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:17:43,176][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:17:43,678][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:17:44,179][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:17:44,679][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:17:45,180][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:17:45,680][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:17:46,182][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:17:46,682][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:17:47,183][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:17:47,683][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:17:48,185][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:17:48,686][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:17:49,187][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:17:49,687][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:17:50,188][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:17:50,689][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:17:51,190][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:17:51,692][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:17:52,193][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:17:52,694][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:17:53,194][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:17:53,695][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:17:54,195][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:17:54,695][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:17:55,195][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:17:55,696][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:17:56,198][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:17:56,700][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:17:57,202][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:17:57,703][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:17:58,205][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:17:58,708][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:17:59,212][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:17:59,715][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:18:00,217][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:18:00,720][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:18:01,222][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:18:01,725][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:18:02,227][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:18:02,729][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:18:03,231][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:18:03,735][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:18:04,237][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:18:04,738][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:18:05,240][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:18:05,741][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:18:06,242][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:18:06,743][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:18:07,244][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:18:07,746][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:18:08,248][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:18:08,753][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:18:09,257][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:18:09,760][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:18:10,264][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:18:10,766][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:18:11,270][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:18:11,774][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21728 tokens. [2026-03-25 20:18:12,410][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.66%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 20:18:13,047][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:18:13,049][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:18:13,051][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:18:13,706][__main__][INFO] - Iteration 211 took 1m 14s (8.85% Gen, 90.27% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 12m 47s. Estimated total time: 61h 55m 47s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 51s, 500 more iterations: 10h 19m 17s. [2026-03-25 20:18:13,709][__main__][INFO] - Starting iteration 211. [2026-03-25 20:18:14,108][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:18:14,109][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:18:14,711][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:18:20,565][__main__][INFO] - Number of regex retries in iteration 211: 1 [2026-03-25 20:18:20,566][__main__][INFO] - agents played in iteration 211 are Bob, Alice [2026-03-25 20:18:21,469][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:18:22,320][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:18:22,778][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:18:23,283][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:18:23,783][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:18:24,284][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:18:24,784][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:18:25,284][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:18:25,785][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:18:26,285][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:18:26,788][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:18:27,289][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:18:27,790][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:18:28,291][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:18:28,792][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:18:29,293][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:18:29,794][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:18:30,295][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:18:30,795][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:18:31,295][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:18:31,796][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:18:32,298][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:18:32,799][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:18:33,298][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:18:33,798][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:18:34,297][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:18:34,798][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:18:35,299][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:18:35,799][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:18:36,302][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:18:36,803][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:18:37,304][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:18:37,804][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:18:38,305][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:18:38,807][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:18:39,309][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:18:39,811][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:18:40,312][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:18:40,810][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:18:41,312][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:18:41,814][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:18:42,315][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:18:42,816][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:18:43,317][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:18:43,818][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:18:44,319][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:18:44,820][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:18:45,321][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:18:45,822][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:18:46,323][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:18:46,827][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:18:47,331][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:18:47,835][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:18:48,338][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:18:48,842][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:18:49,345][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:18:49,848][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:18:50,351][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:18:50,853][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:18:51,354][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:18:51,856][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:18:52,357][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:18:52,858][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:18:53,359][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:18:53,860][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:18:54,362][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:18:54,862][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:18:55,362][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:18:55,862][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:18:56,362][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:18:56,862][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:18:57,362][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:18:57,862][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:18:58,362][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:18:58,863][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:18:59,363][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:18:59,864][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:19:00,365][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:19:00,866][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:19:01,367][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:19:01,868][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:19:02,368][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:19:02,868][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:19:03,370][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:19:03,871][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:19:04,371][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:19:04,872][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:19:05,373][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:19:05,874][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:19:06,374][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:19:06,874][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:19:07,375][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:19:07,876][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:19:08,377][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:19:08,878][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:19:09,379][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:19:09,880][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:19:10,380][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:19:10,881][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:19:11,383][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:19:11,883][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:19:12,384][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:19:12,884][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:19:13,385][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:19:13,885][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:19:14,386][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:19:14,885][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:19:15,385][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:19:15,885][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:19:16,386][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:19:16,888][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:19:17,388][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:19:17,889][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:19:18,390][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:19:18,893][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:19:19,395][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:19:19,897][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:19:20,400][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:19:20,901][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:19:21,403][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:19:21,903][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:19:22,406][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:19:22,907][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:19:23,410][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:19:23,911][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:19:24,413][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:19:24,914][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:19:25,417][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:19:25,919][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:19:26,421][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21719 tokens. [2026-03-25 20:19:27,056][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:04 [2026-03-25 20:19:27,782][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:19:27,784][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:19:27,785][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:19:28,425][__main__][INFO] - Iteration 212 took 1m 14s (8.69% Gen, 90.45% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 11m 36s. Estimated total time: 61h 55m 51s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 51s, 500 more iterations: 10h 19m 18s. [2026-03-25 20:19:28,428][__main__][INFO] - Starting iteration 212. [2026-03-25 20:19:28,829][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:19:28,830][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:19:29,403][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:19:29,409][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:19:35,545][__main__][INFO] - Number of regex retries in iteration 212: 2 [2026-03-25 20:19:35,546][__main__][INFO] - agents played in iteration 212 are Bob, Alice [2026-03-25 20:19:36,457][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:19:37,046][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:19:37,505][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:19:38,012][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:19:38,515][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:19:39,019][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:19:39,522][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:19:40,023][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:19:40,524][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:19:41,026][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:19:41,532][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:19:42,035][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:19:42,538][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:19:43,041][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:19:43,544][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:19:44,048][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:19:44,553][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:19:45,057][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:19:45,559][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:19:46,062][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:19:46,564][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:19:47,067][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:19:47,569][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:19:48,073][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:19:48,575][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:19:49,077][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:19:49,580][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:19:50,082][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:19:50,594][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:19:51,097][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:19:51,599][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:19:52,101][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:19:52,604][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:19:53,106][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:19:53,609][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:19:54,112][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:19:54,613][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:19:55,115][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:19:55,618][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:19:56,120][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:19:56,623][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:19:57,124][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:19:57,625][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:19:58,127][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:19:58,628][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:19:59,129][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:19:59,630][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:20:00,131][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:20:00,632][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:20:01,133][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:20:01,634][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:20:02,136][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:20:02,637][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:20:03,138][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:20:03,639][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:20:04,139][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:20:04,640][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:20:05,140][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:20:05,643][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:20:06,144][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:20:06,646][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:20:07,149][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:20:07,652][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:20:08,154][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:20:08,656][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:20:09,157][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:20:09,659][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:20:10,159][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:20:10,661][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:20:11,162][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:20:11,665][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:20:12,166][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:20:12,669][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:20:13,171][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:20:13,673][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:20:14,176][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:20:14,678][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:20:15,180][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:20:15,681][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:20:16,183][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:20:16,685][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:20:17,186][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:20:17,688][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:20:18,191][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:20:18,693][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:20:19,194][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:20:19,696][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:20:20,197][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:20:20,699][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:20:21,199][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:20:21,700][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:20:22,201][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:20:22,702][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:20:23,204][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:20:23,705][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:20:24,206][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:20:24,707][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:20:25,210][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:20:25,711][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:20:26,213][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:20:26,714][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:20:27,217][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:20:27,718][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:20:28,220][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:20:28,721][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:20:29,223][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:20:29,724][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:20:30,224][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:20:30,725][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:20:31,227][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:20:31,729][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:20:32,231][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:20:32,731][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:20:33,233][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:20:33,733][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:20:34,234][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:20:34,735][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:20:35,236][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:20:35,737][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:20:36,239][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:20:36,739][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:20:37,240][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:20:37,742][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:20:38,244][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:20:38,745][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:20:39,248][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:20:39,749][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:20:40,251][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:20:40,754][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:20:41,258][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 20:20:41,895][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 20:20:42,641][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:20:42,643][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:20:42,645][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:20:43,325][__main__][INFO] - Iteration 213 took 1m 14s (9.02% Gen, 90.07% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 19m 18s. Estimated total time: 62h 4m 48s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 9s, 500 more iterations: 10h 20m 48s. [2026-03-25 20:20:43,327][__main__][INFO] - Starting iteration 213. [2026-03-25 20:20:43,727][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:20:43,727][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:20:44,989][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:20:50,632][__main__][INFO] - Number of regex retries in iteration 213: 1 [2026-03-25 20:20:50,633][__main__][INFO] - agents played in iteration 213 are Bob, Alice [2026-03-25 20:20:51,589][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:20:52,445][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:20:52,904][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:20:53,412][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:20:53,914][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:20:54,417][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:20:54,919][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:20:55,421][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:20:55,922][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:20:56,424][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:20:56,926][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:20:57,427][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:20:57,929][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:20:58,430][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:20:58,931][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:20:59,432][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:20:59,934][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:21:00,435][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:21:00,937][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:21:01,438][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:21:01,939][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:21:02,440][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:21:02,940][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:21:03,442][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:21:03,944][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:21:04,445][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:21:04,947][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:21:05,447][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:21:05,950][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:21:06,451][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:21:06,953][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:21:07,454][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:21:07,955][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:21:08,457][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:21:08,958][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:21:09,467][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:21:09,971][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:21:10,473][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:21:10,975][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:21:11,480][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:21:11,982][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:21:12,484][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:21:12,986][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:21:13,488][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:21:13,993][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:21:14,495][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:21:14,997][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:21:15,509][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:21:16,013][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:21:16,516][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:21:17,022][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:21:17,526][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:21:18,028][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:21:18,532][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:21:19,036][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:21:19,539][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:21:20,042][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:21:20,546][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:21:21,048][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:21:21,553][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:21:22,055][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:21:22,558][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:21:23,060][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:21:23,562][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:21:24,064][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:21:24,566][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:21:25,068][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:21:25,570][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:21:26,073][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:21:26,575][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:21:27,077][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:21:27,579][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:21:28,080][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:21:28,581][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:21:29,083][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:21:29,585][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:21:30,087][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:21:30,590][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:21:31,092][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:21:31,595][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:21:32,097][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:21:32,599][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:21:33,100][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:21:33,600][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:21:34,100][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:21:34,600][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:21:35,100][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:21:35,601][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:21:36,101][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:21:36,603][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:21:37,106][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:21:37,609][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:21:38,110][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:21:38,614][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:21:39,118][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:21:39,621][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:21:40,124][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:21:40,626][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:21:41,127][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:21:41,629][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:21:42,132][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:21:42,632][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:21:43,134][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:21:43,635][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:21:44,136][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:21:44,637][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:21:45,139][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:21:45,640][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:21:46,142][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:21:46,643][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:21:47,145][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:21:47,645][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:21:48,146][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:21:48,647][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:21:49,150][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:21:49,652][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:21:50,154][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:21:50,656][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:21:51,159][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:21:51,661][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:21:52,165][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:21:52,667][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:21:53,169][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:21:53,671][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:21:54,174][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:21:54,676][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:21:55,177][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:21:55,679][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:21:56,180][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:21:56,682][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 20:21:57,305][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 20:21:58,041][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:21:58,043][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:21:58,044][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:21:58,738][__main__][INFO] - Iteration 214 took 1m 15s (9.21% Gen, 89.87% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 43m 50s. Estimated total time: 62h 30m 35s. Time estimates for 10 more iterations: 12m 30s, 100 more iterations: 2h 5m 1s, 500 more iterations: 10h 25m 5s. [2026-03-25 20:21:58,740][__main__][INFO] - Starting iteration 214. [2026-03-25 20:21:59,143][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:21:59,144][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:22:01,435][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:22:05,983][__main__][INFO] - Number of regex retries in iteration 214: 1 [2026-03-25 20:22:05,984][__main__][INFO] - agents played in iteration 214 are Bob, Alice [2026-03-25 20:22:06,897][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:22:07,482][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:22:07,940][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:22:08,446][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:22:08,950][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:22:09,454][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:22:09,957][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:22:10,459][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:22:10,961][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:22:11,466][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:22:11,970][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:22:12,472][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:22:12,975][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:22:13,477][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:22:13,980][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:22:14,482][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:22:14,985][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:22:15,487][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:22:15,990][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:22:16,492][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:22:16,994][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:22:17,497][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:22:17,999][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:22:18,500][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:22:19,002][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:22:19,504][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:22:20,005][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:22:20,506][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:22:21,008][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:22:21,509][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:22:22,012][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:22:22,513][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:22:23,015][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:22:23,517][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:22:24,020][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:22:24,522][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:22:25,025][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:22:25,528][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:22:26,032][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:22:26,535][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:22:27,038][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:22:27,540][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:22:28,042][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:22:28,544][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:22:29,046][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:22:29,549][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:22:30,051][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:22:30,554][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:22:31,057][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:22:31,559][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:22:32,060][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:22:32,562][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:22:33,063][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:22:33,563][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:22:34,065][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:22:34,566][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:22:35,067][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:22:35,569][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:22:36,070][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:22:36,571][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:22:37,073][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:22:37,574][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:22:38,075][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:22:38,576][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:22:39,077][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:22:39,578][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:22:40,080][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:22:40,583][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:22:41,086][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:22:41,592][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:22:42,095][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:22:42,598][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:22:43,101][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:22:43,604][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:22:44,107][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:22:44,609][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:22:45,113][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:22:45,616][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:22:46,118][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:22:46,621][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:22:47,124][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:22:47,626][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:22:48,127][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:22:48,631][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:22:49,133][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:22:49,636][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:22:50,138][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:22:50,640][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:22:51,141][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:22:51,642][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:22:52,143][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:22:52,645][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:22:53,146][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:22:53,647][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:22:54,147][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:22:54,651][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:22:55,152][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:22:55,654][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:22:56,156][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:22:56,659][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:22:57,161][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:22:57,663][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:22:58,166][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:22:58,668][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:22:59,171][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:22:59,674][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:23:00,176][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:23:00,678][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:23:01,180][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:23:01,682][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:23:02,184][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:23:02,686][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:23:03,191][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:23:03,693][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:23:04,195][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:23:04,696][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:23:05,197][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:23:05,698][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:23:06,200][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:23:06,703][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:23:07,206][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:23:07,707][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:23:08,209][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:23:08,711][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:23:09,214][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:23:09,715][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:23:10,218][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:23:10,720][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:23:11,223][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:23:11,726][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 20:23:12,348][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 20:23:13,083][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:23:13,085][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:23:13,086][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:23:13,722][__main__][INFO] - Iteration 215 took 1m 14s (9.17% Gen, 89.97% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 20m 59s. Estimated total time: 62h 8m 59s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 17s, 500 more iterations: 10h 21m 29s. [2026-03-25 20:23:13,725][__main__][INFO] - Starting iteration 215. [2026-03-25 20:23:14,123][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:23:14,124][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:23:17,284][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:23:20,626][__main__][INFO] - Number of regex retries in iteration 215: 1 [2026-03-25 20:23:20,627][__main__][INFO] - agents played in iteration 215 are Bob, Alice [2026-03-25 20:23:21,544][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:23:22,128][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:23:22,587][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:23:23,094][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:23:23,596][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:23:24,098][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:23:24,600][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:23:25,101][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:23:25,602][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:23:26,104][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:23:26,605][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:23:27,105][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:23:27,606][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:23:28,106][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:23:28,606][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:23:29,106][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:23:29,607][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:23:30,107][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:23:30,607][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:23:31,107][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:23:31,607][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:23:32,108][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:23:32,609][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:23:33,110][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:23:33,611][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:23:34,113][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:23:34,615][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:23:35,116][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:23:35,618][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:23:36,119][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:23:36,620][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:23:37,121][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:23:37,622][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:23:38,123][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:23:38,627][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:23:39,130][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:23:39,632][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:23:40,134][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:23:40,637][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:23:41,139][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:23:41,644][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:23:42,146][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:23:42,647][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:23:43,148][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:23:43,648][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:23:44,152][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:23:44,654][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:23:45,155][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:23:45,657][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:23:46,158][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:23:46,662][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:23:47,166][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:23:47,669][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:23:48,173][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:23:48,674][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:23:49,177][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:23:49,680][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:23:50,183][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:23:50,681][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:23:51,181][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:23:51,680][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:23:52,178][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:23:52,676][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:23:53,176][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:23:53,674][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:23:54,175][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:23:54,676][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:23:55,177][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:23:55,677][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:23:56,179][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:23:56,680][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:23:57,181][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:23:57,682][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:23:58,183][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:23:58,683][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:23:59,182][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:23:59,682][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:24:00,181][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:24:00,682][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:24:01,182][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:24:01,682][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:24:02,182][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:24:02,681][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:24:03,181][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:24:03,680][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:24:04,179][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:24:04,679][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:24:05,179][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:24:05,678][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:24:06,177][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:24:06,677][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:24:07,177][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:24:07,677][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:24:08,177][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:24:08,678][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:24:09,178][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:24:09,678][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:24:10,179][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:24:10,681][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:24:11,183][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:24:11,685][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:24:12,188][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:24:12,690][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:24:13,192][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:24:13,694][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:24:14,196][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:24:14,698][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:24:15,199][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:24:15,700][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:24:16,200][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:24:16,701][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:24:17,203][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:24:17,704][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:24:18,205][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:24:18,708][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:24:19,212][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:24:19,714][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:24:20,218][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:24:20,720][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:24:21,222][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:24:21,724][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:24:22,226][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:24:22,727][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:24:23,226][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:24:23,725][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:24:24,226][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:24:24,726][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:24:25,227][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:24:25,727][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:24:26,229][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21654 tokens. [2026-03-25 20:24:26,851][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:04 [2026-03-25 20:24:27,578][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:24:27,581][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:24:27,583][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:24:28,288][__main__][INFO] - Iteration 216 took 1m 14s (8.77% Gen, 90.28% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 56h 59m 2s. Estimated total time: 61h 48m 17s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 36s, 500 more iterations: 10h 18m 2s. [2026-03-25 20:24:28,290][__main__][INFO] - Starting iteration 216. [2026-03-25 20:24:28,691][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:24:28,692][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:24:35,169][__main__][INFO] - Number of regex retries in iteration 216: 0 [2026-03-25 20:24:35,170][__main__][INFO] - agents played in iteration 216 are Bob, Alice [2026-03-25 20:24:36,086][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:24:36,664][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:24:37,121][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:24:37,627][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:24:38,138][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:24:38,641][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:24:39,142][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:24:39,643][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:24:40,145][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:24:40,647][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:24:41,149][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:24:41,652][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:24:42,154][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:24:42,655][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:24:43,157][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:24:43,662][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:24:44,163][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:24:44,664][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:24:45,164][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:24:45,665][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:24:46,166][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:24:46,667][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:24:47,168][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:24:47,669][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:24:48,170][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:24:48,671][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:24:49,174][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:24:49,677][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:24:50,178][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:24:50,680][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:24:51,180][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:24:51,682][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:24:52,183][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:24:52,686][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:24:53,187][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:24:53,687][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:24:54,187][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:24:54,687][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:24:55,187][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:24:55,688][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:24:56,189][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:24:56,688][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:24:57,189][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:24:57,692][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:24:58,194][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:24:58,697][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:24:59,200][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:24:59,702][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:25:00,205][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:25:00,707][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:25:01,212][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:25:01,714][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:25:02,215][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:25:02,716][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:25:03,217][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:25:03,718][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:25:04,219][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:25:04,720][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:25:05,224][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:25:05,728][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:25:06,230][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:25:06,732][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:25:07,235][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:25:07,738][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:25:08,240][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:25:08,743][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:25:09,243][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:25:09,743][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:25:10,244][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:25:10,745][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:25:11,248][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:25:11,749][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:25:12,251][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:25:12,751][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:25:13,253][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:25:13,754][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:25:14,255][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:25:14,756][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:25:15,257][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:25:15,758][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:25:16,259][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:25:16,759][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:25:17,259][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:25:17,759][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:25:18,260][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:25:18,761][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:25:19,262][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:25:19,762][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:25:20,264][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:25:20,764][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:25:21,264][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:25:21,765][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:25:22,264][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:25:22,765][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:25:23,266][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:25:23,766][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:25:24,266][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:25:24,766][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:25:25,266][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:25:25,765][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:25:26,265][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:25:26,764][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:25:27,264][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:25:27,764][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:25:28,264][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:25:28,764][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:25:29,265][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:25:29,765][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:25:30,267][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:25:30,770][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:25:31,271][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:25:31,772][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:25:32,273][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:25:32,774][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:25:33,275][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:25:33,776][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:25:34,276][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:25:34,777][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:25:35,277][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:25:35,776][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:25:36,277][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:25:36,777][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:25:37,280][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:25:37,781][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:25:38,285][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:25:38,789][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:25:39,292][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:25:39,794][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:25:40,297][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:25:40,800][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21750 tokens. [2026-03-25 20:25:41,430][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.65%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-25 20:25:42,161][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:25:42,164][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:25:42,165][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:25:42,923][__main__][INFO] - Iteration 217 took 1m 14s (8.73% Gen, 90.25% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 1m 8s. Estimated total time: 61h 51m 38s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 43s, 500 more iterations: 10h 18m 36s. [2026-03-25 20:25:42,925][__main__][INFO] - Starting iteration 217. [2026-03-25 20:25:43,327][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:25:43,327][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:25:49,679][__main__][INFO] - Number of regex retries in iteration 217: 0 [2026-03-25 20:25:49,680][__main__][INFO] - agents played in iteration 217 are Bob, Alice [2026-03-25 20:25:50,596][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:25:51,177][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:25:51,636][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:25:52,143][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:25:52,644][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:25:53,146][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:25:53,649][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:25:54,152][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:25:54,654][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:25:55,157][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:25:55,658][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:25:56,160][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:25:56,662][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:25:57,163][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:25:57,664][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:25:58,166][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:25:58,668][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:25:59,171][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:25:59,672][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:26:00,173][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:26:00,674][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:26:01,176][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:26:01,677][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:26:02,178][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:26:02,679][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:26:03,180][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:26:03,682][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:26:04,184][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:26:04,686][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:26:05,189][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:26:05,692][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:26:06,194][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:26:06,696][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:26:07,198][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:26:07,702][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:26:08,207][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:26:08,711][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:26:09,215][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:26:09,718][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:26:10,221][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:26:10,725][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:26:11,231][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:26:11,735][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:26:12,238][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:26:12,742][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:26:13,244][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:26:13,747][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:26:14,249][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:26:14,752][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:26:15,255][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:26:15,757][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:26:16,259][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:26:16,761][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:26:17,263][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:26:17,764][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:26:18,264][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:26:18,767][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:26:19,269][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:26:19,773][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:26:20,275][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:26:20,778][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:26:21,280][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:26:21,784][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:26:22,287][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:26:22,790][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:26:23,293][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:26:23,795][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:26:24,297][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:26:24,798][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:26:25,299][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:26:25,799][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:26:26,301][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:26:26,802][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:26:27,303][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:26:27,805][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:26:28,306][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:26:28,810][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:26:29,312][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:26:29,814][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:26:30,316][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:26:30,818][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:26:31,321][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:26:31,823][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:26:32,324][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:26:32,825][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:26:33,326][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:26:33,828][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:26:34,329][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:26:34,831][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:26:35,332][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:26:35,835][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:26:36,337][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:26:36,839][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:26:37,342][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:26:37,844][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:26:38,345][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:26:38,846][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:26:39,347][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:26:39,850][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:26:40,353][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:26:40,855][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:26:41,360][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:26:41,861][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:26:42,364][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:26:42,866][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:26:43,369][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:26:43,872][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:26:44,374][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:26:44,876][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:26:45,378][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:26:45,880][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:26:46,381][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:26:46,883][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:26:47,383][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:26:47,885][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:26:48,386][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:26:48,887][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:26:49,387][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:26:49,887][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:26:50,388][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:26:50,888][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:26:51,392][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:26:51,894][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:26:52,398][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:26:52,900][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:26:53,401][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:26:53,902][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:26:54,404][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:26:54,908][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:26:55,411][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21698 tokens. [2026-03-25 20:26:56,025][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.31%, Current % of VRAM taken: 60.66%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:04 [2026-03-25 20:26:56,751][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:26:56,753][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:26:56,755][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:26:57,382][__main__][INFO] - Iteration 218 took 1m 14s (8.58% Gen, 90.57% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 51m 1s. Estimated total time: 61h 42m 46s. Time estimates for 10 more iterations: 12m 20s, 100 more iterations: 2h 3m 25s, 500 more iterations: 10h 17m 7s. [2026-03-25 20:26:57,384][__main__][INFO] - Starting iteration 218. [2026-03-25 20:26:57,783][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:26:57,784][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:26:59,959][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:27:04,512][__main__][INFO] - Number of regex retries in iteration 218: 1 [2026-03-25 20:27:04,513][__main__][INFO] - agents played in iteration 218 are Bob, Alice [2026-03-25 20:27:05,422][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:27:06,005][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:27:06,462][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:27:06,967][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:27:07,468][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:27:07,969][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:27:08,472][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:27:08,973][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:27:09,474][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:27:09,975][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:27:10,478][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:27:10,978][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:27:11,481][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:27:11,981][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:27:12,482][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:27:12,984][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:27:13,485][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:27:13,985][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:27:14,488][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:27:14,991][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:27:15,493][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:27:15,994][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:27:16,496][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:27:16,998][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:27:17,499][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:27:18,000][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:27:18,500][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:27:19,001][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:27:19,501][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:27:20,001][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:27:20,501][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:27:21,001][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:27:21,502][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:27:22,002][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:27:22,503][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:27:23,004][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:27:23,503][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:27:24,003][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:27:24,504][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:27:25,005][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:27:25,505][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:27:26,005][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:27:26,506][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:27:27,007][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:27:27,511][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:27:28,012][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:27:28,513][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:27:29,014][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:27:29,515][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:27:30,017][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:27:30,521][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:27:31,022][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:27:31,524][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:27:32,026][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:27:32,528][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:27:33,029][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:27:33,533][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:27:34,034][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:27:34,536][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:27:35,036][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:27:35,536][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:27:36,036][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:27:36,537][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:27:37,036][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:27:37,537][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:27:38,038][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:27:38,539][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:27:39,039][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:27:39,539][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:27:40,039][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:27:40,540][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:27:41,041][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:27:41,543][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:27:42,045][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:27:42,545][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:27:43,046][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:27:43,549][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:27:44,051][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:27:44,552][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:27:45,052][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:27:45,553][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:27:46,054][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:27:46,556][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:27:47,057][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:27:47,558][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:27:48,058][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:27:48,559][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:27:49,060][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:27:49,560][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:27:50,060][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:27:50,560][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:27:51,060][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:27:51,560][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:27:52,060][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:27:52,559][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:27:53,060][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:27:53,560][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:27:54,061][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:27:54,561][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:27:55,061][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:27:55,561][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:27:56,061][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:27:56,561][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:27:57,061][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:27:57,562][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:27:58,061][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:27:58,563][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:27:59,063][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:27:59,564][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:28:00,065][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:28:00,566][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:28:01,068][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:28:01,569][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:28:02,069][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:28:02,571][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:28:03,073][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:28:03,574][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:28:04,077][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:28:04,578][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:28:05,079][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:28:05,579][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:28:06,080][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:28:06,580][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:28:07,080][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:28:07,579][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:28:08,079][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:28:08,578][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:28:09,077][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:28:09,577][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:28:10,076][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 20:28:10,693][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 20:28:11,425][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:28:11,427][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:28:11,429][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:28:12,066][__main__][INFO] - Iteration 219 took 1m 14s (9.06% Gen, 90.08% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 57h 1m 10s. Estimated total time: 61h 54m 9s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 48s, 500 more iterations: 10h 19m 1s. [2026-03-25 20:28:12,068][__main__][INFO] - Starting iteration 219. [2026-03-25 20:28:12,468][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:28:12,469][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:28:19,731][__main__][INFO] - Number of regex retries in iteration 219: 0 [2026-03-25 20:28:19,732][__main__][INFO] - agents played in iteration 219 are Bob, Alice [2026-03-25 20:28:20,647][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:28:21,229][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:28:21,688][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:28:22,194][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:28:22,696][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:28:23,198][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:28:23,699][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:28:24,200][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:28:24,700][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:28:25,201][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:28:25,705][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:28:26,207][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:28:26,709][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:28:27,213][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:28:27,715][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:28:28,217][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:28:28,719][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:28:29,222][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:28:29,723][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:28:30,225][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:28:30,726][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:28:31,227][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:28:31,728][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:28:32,229][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:28:32,730][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:28:33,231][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:28:33,733][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:28:34,234][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:28:34,735][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:28:35,237][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:28:35,739][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:28:36,240][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:28:36,740][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:28:37,241][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:28:37,743][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:28:38,244][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:28:38,746][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:28:39,247][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:28:39,748][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:28:40,252][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:28:40,755][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:28:41,257][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:28:41,759][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:28:42,258][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:28:42,759][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:28:43,259][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:28:43,760][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:28:44,259][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:28:44,760][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:28:45,259][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:28:45,759][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:28:46,259][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:28:46,759][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:28:47,259][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:28:47,760][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:28:48,260][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:28:48,760][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:28:49,259][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:28:49,760][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:28:50,260][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:28:50,761][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:28:51,260][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:28:51,760][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:28:52,259][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:28:52,759][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:28:53,258][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:28:53,759][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:28:54,259][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:28:54,759][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:28:55,258][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:28:55,759][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:28:56,259][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:28:56,759][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:28:57,259][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:28:57,761][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:28:58,262][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:28:58,763][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:28:59,263][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:28:59,764][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:29:00,265][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:29:00,766][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:29:01,267][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:29:01,767][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:29:02,267][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:29:02,767][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:29:03,269][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:29:03,770][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:29:04,271][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:29:04,771][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:29:05,271][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:29:05,771][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:29:06,271][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:29:06,772][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:29:07,272][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:29:07,772][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:29:08,272][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:29:08,772][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:29:09,271][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:29:09,772][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:29:10,272][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:29:10,773][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:29:11,275][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:29:11,776][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:29:12,277][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:29:12,777][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:29:13,277][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:29:13,776][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:29:14,277][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:29:14,776][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:29:15,276][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:29:15,775][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:29:16,274][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:29:16,773][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:29:17,273][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:29:17,772][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:29:18,271][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:29:18,770][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:29:19,269][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:29:19,768][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:29:20,266][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:29:20,765][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:29:21,264][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:29:21,764][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:29:22,262][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:29:22,761][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:29:23,261][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:29:23,760][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:29:24,258][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:29:24,757][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:29:25,256][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 20:29:25,862][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:04 [2026-03-25 20:29:26,586][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:29:26,588][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:29:26,589][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:29:27,285][__main__][INFO] - Iteration 220 took 1m 14s (9.71% Gen, 89.36% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 57h 26m 38s. Estimated total time: 62h 20m 52s. Time estimates for 10 more iterations: 12m 28s, 100 more iterations: 2h 4m 41s, 500 more iterations: 10h 23m 28s. [2026-03-25 20:29:27,287][__main__][INFO] - Starting iteration 220. [2026-03-25 20:29:27,686][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:29:27,686][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:29:28,276][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:29:30,385][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:29:33,678][mllm.models.large_language_model_local][WARNING] - Response Proposals often benefit from being strategic, especially when the per-item values can significantly influence outcomes. Given the information: - Hats: You value 10, Bob values 1. - Books: You value 1, Bob values 10. - Balls: You value 10, Bob values 10. Given that you have the highest values for both hats and balls and a decent value for books, it makes sense to propose keeping as many of each high-value item as possible. However, we must also consider that if Bob's proposals are excessively high, the items may not be allocated to us at all. A strategic approach might be to propose taking most of the items you value highly, but leaving enough for Bob to ensure a reasonable allocation, especially for the books where your value is quite low. Here's a proposed split: - 10 hats (you value these the most) - 0 books (keep a few more for Bob to keep the allocation fair while maximizing your value) - 10 balls (you value these second-highest) So, the proposal would be: Proposal: 10 hats, 0 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:29:36,240][__main__][INFO] - Number of regex retries in iteration 220: 3 [2026-03-25 20:29:36,241][__main__][INFO] - agents played in iteration 220 are Bob, Alice [2026-03-25 20:29:37,154][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:29:37,734][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:29:38,194][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:29:38,700][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:29:39,203][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:29:39,705][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:29:40,207][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:29:40,710][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:29:41,214][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:29:41,717][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:29:42,220][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:29:42,722][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:29:43,224][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:29:43,726][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:29:44,229][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:29:44,731][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:29:45,234][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:29:45,736][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:29:46,238][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:29:46,739][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:29:47,241][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:29:47,743][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:29:48,245][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:29:48,747][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:29:49,248][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:29:49,752][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:29:50,253][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:29:50,754][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:29:51,254][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:29:51,755][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:29:52,256][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:29:52,757][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:29:53,258][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:29:53,759][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:29:54,260][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:29:54,762][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:29:55,262][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:29:55,763][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:29:56,264][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:29:56,765][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:29:57,266][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:29:57,767][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:29:58,268][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:29:58,769][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:29:59,271][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:29:59,772][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:30:00,273][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:30:00,773][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:30:01,274][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:30:01,775][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:30:02,277][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:30:02,779][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:30:03,281][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:30:03,782][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:30:04,284][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:30:04,786][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:30:05,288][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:30:05,791][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:30:06,291][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:30:06,791][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:30:07,292][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:30:07,791][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:30:08,292][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:30:08,792][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:30:09,291][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:30:09,791][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:30:10,292][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:30:10,795][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:30:11,298][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:30:11,801][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:30:12,302][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:30:12,805][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:30:13,306][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:30:13,808][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:30:14,311][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:30:14,813][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:30:15,314][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:30:15,817][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:30:16,319][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:30:16,820][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:30:17,323][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:30:17,826][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:30:18,326][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:30:18,826][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:30:19,326][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:30:19,827][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:30:20,326][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:30:20,828][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:30:21,329][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:30:21,830][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:30:22,329][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:30:22,829][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:30:23,328][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:30:23,827][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:30:24,329][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:30:24,828][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:30:25,328][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:30:25,828][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:30:26,328][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:30:26,829][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:30:27,329][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:30:27,829][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:30:28,330][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:30:28,832][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:30:29,332][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:30:29,832][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:30:30,332][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:30:30,832][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:30:31,332][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:30:31,832][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:30:32,332][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:30:32,832][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:30:33,331][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:30:33,832][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:30:34,332][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:30:34,832][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:30:35,333][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:30:35,834][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:30:36,335][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:30:36,836][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:30:37,336][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:30:37,836][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:30:38,335][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:30:38,834][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:30:39,333][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:30:39,832][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:30:40,331][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:30:40,832][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:30:41,331][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:30:41,831][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 20:30:42,440][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:04 [2026-03-25 20:30:43,169][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:30:43,171][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:30:43,173][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:30:43,810][__main__][INFO] - Iteration 221 took 1m 16s (11.24% Gen, 87.92% Train). Generation: 8s, Training: 1m 6s. Estimated remaining time: 58h 30m 45s. Estimated total time: 63h 26m 15s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 52s, 500 more iterations: 10h 34m 22s. [2026-03-25 20:30:43,812][__main__][INFO] - Starting iteration 221. [2026-03-25 20:30:44,209][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:30:44,210][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:30:44,790][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:30:50,684][__main__][INFO] - Number of regex retries in iteration 221: 1 [2026-03-25 20:30:50,684][__main__][INFO] - agents played in iteration 221 are Bob, Alice [2026-03-25 20:30:51,596][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:30:52,178][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:30:52,636][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:30:53,142][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:30:53,643][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:30:54,143][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:30:54,643][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:30:55,143][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:30:55,643][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:30:56,144][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:30:56,643][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:30:57,141][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:30:57,640][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:30:58,139][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:30:58,639][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:30:59,139][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:30:59,638][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:31:00,137][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:31:00,638][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:31:01,139][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:31:01,639][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:31:02,139][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:31:02,640][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:31:03,140][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:31:03,640][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:31:04,140][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:31:04,639][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:31:05,139][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:31:05,638][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:31:06,137][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:31:06,637][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:31:07,138][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:31:07,638][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:31:08,138][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:31:08,640][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:31:09,141][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:31:09,643][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:31:10,144][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:31:10,645][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:31:11,144][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:31:11,645][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:31:12,146][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:31:12,645][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:31:13,145][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:31:13,644][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:31:14,144][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:31:14,644][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:31:15,144][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:31:15,643][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:31:16,142][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:31:16,644][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:31:17,144][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:31:17,644][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:31:18,144][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:31:18,644][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:31:19,145][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:31:19,645][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:31:20,146][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:31:20,646][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:31:21,146][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:31:21,645][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:31:22,147][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:31:22,650][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:31:23,153][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:31:23,657][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:31:24,158][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:31:24,663][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:31:25,163][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:31:25,669][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:31:26,170][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:31:26,676][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:31:27,178][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:31:27,678][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:31:28,178][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:31:28,677][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:31:29,176][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:31:29,677][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:31:30,177][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:31:30,675][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:31:31,173][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:31:31,672][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:31:32,171][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:31:32,672][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:31:33,172][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:31:33,672][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:31:34,173][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:31:34,673][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:31:35,177][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:31:35,678][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:31:36,178][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:31:36,678][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:31:37,175][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:31:37,674][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:31:38,174][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:31:38,672][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:31:39,172][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:31:39,676][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:31:40,177][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:31:40,678][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:31:41,178][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:31:41,679][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:31:42,179][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:31:42,680][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:31:43,180][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:31:43,680][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:31:44,180][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:31:44,684][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:31:45,186][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:31:45,687][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:31:46,188][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:31:46,687][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:31:47,187][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:31:47,686][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:31:48,186][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:31:48,686][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:31:49,186][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:31:49,688][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:31:50,190][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:31:50,692][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:31:51,193][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:31:51,693][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:31:52,194][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:31:52,694][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:31:53,193][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:31:53,693][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:31:54,193][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:31:54,694][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:31:55,200][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:31:55,701][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:31:56,200][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21688 tokens. [2026-03-25 20:31:56,816][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 20:31:57,545][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:31:57,548][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:31:57,550][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:31:58,184][__main__][INFO] - Iteration 222 took 1m 13s (8.75% Gen, 90.39% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 56h 42m 1s. Estimated total time: 61h 38m 46s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 17s, 500 more iterations: 10h 16m 27s. [2026-03-25 20:31:58,188][__main__][INFO] - Starting iteration 222. [2026-03-25 20:31:58,587][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:31:58,587][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:32:01,250][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:32:04,650][__main__][INFO] - Number of regex retries in iteration 222: 1 [2026-03-25 20:32:04,651][__main__][INFO] - agents played in iteration 222 are Bob, Alice [2026-03-25 20:32:05,552][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:32:06,136][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:32:06,592][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:32:07,097][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:32:07,598][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:32:08,099][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:32:08,600][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:32:09,100][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:32:09,601][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:32:10,103][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:32:10,611][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:32:11,114][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:32:11,616][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:32:12,118][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:32:12,621][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:32:13,122][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:32:13,624][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:32:14,125][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:32:14,626][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:32:15,126][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:32:15,647][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:32:16,151][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:32:16,651][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:32:17,151][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:32:17,653][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:32:18,155][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:32:18,658][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:32:19,160][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:32:19,662][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:32:20,162][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:32:20,669][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:32:21,172][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:32:21,673][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:32:22,174][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:32:22,675][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:32:23,175][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:32:23,675][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:32:24,176][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:32:24,676][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:32:25,176][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:32:25,681][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:32:26,183][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:32:26,682][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:32:27,182][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:32:27,682][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:32:28,182][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:32:28,682][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:32:29,183][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:32:29,679][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:32:30,179][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:32:30,686][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:32:31,189][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:32:31,692][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:32:32,194][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:32:32,695][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:32:33,197][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:32:33,698][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:32:34,199][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:32:34,700][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:32:35,201][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:32:35,702][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:32:36,204][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:32:36,705][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:32:37,208][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:32:37,711][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:32:38,212][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:32:38,714][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:32:39,214][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:32:39,715][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:32:40,217][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:32:40,717][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:32:41,218][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:32:41,719][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:32:42,219][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:32:42,721][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:32:43,222][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:32:43,724][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:32:44,225][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:32:44,728][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:32:45,231][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:32:45,733][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:32:46,235][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:32:46,737][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:32:47,238][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:32:47,739][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:32:48,238][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:32:48,738][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:32:49,238][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:32:49,740][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:32:50,241][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:32:50,743][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:32:51,245][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:32:51,748][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:32:52,251][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:32:52,754][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:32:53,257][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:32:53,759][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:32:54,261][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:32:54,762][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:32:55,263][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:32:55,763][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:32:56,264][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:32:56,765][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:32:57,265][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:32:57,765][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:32:58,267][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:32:58,768][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:32:59,269][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:32:59,770][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:33:00,271][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:33:00,772][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:33:01,273][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:33:01,774][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:33:02,275][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:33:02,776][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:33:03,278][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:33:03,778][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:33:04,280][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:33:04,781][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:33:05,282][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:33:05,783][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:33:06,285][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:33:06,786][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:33:07,289][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:33:07,791][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:33:08,292][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:33:08,793][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:33:09,295][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:33:09,796][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:33:10,297][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21720 tokens. [2026-03-25 20:33:10,933][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-25 20:33:11,662][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:33:11,664][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:33:11,666][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:33:12,381][__main__][INFO] - Iteration 223 took 1m 13s (8.22% Gen, 90.81% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 31m 45s. Estimated total time: 61h 29m 44s. Time estimates for 10 more iterations: 12m 17s, 100 more iterations: 2h 2m 59s, 500 more iterations: 10h 14m 57s. [2026-03-25 20:33:12,383][__main__][INFO] - Starting iteration 223. [2026-03-25 20:33:12,783][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:33:12,783][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:33:14,876][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:33:16,052][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:33:19,256][__main__][INFO] - Number of regex retries in iteration 223: 2 [2026-03-25 20:33:19,257][__main__][INFO] - agents played in iteration 223 are Bob, Alice [2026-03-25 20:33:20,155][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:33:20,742][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:33:21,198][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:33:21,702][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:33:22,202][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:33:22,702][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:33:23,201][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:33:23,701][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:33:24,201][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:33:24,700][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:33:25,202][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:33:25,702][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:33:26,202][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:33:26,702][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:33:27,202][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:33:27,702][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:33:28,202][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:33:28,702][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:33:29,202][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:33:29,702][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:33:30,202][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:33:30,701][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:33:31,202][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:33:31,701][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:33:32,201][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:33:32,700][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:33:33,200][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:33:33,701][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:33:34,200][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:33:34,700][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:33:35,199][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:33:35,699][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:33:36,199][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:33:36,700][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:33:37,203][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:33:37,704][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:33:38,206][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:33:38,708][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:33:39,212][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:33:39,714][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:33:40,217][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:33:40,719][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:33:41,219][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:33:41,719][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:33:42,219][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:33:42,720][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:33:43,221][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:33:43,721][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:33:44,221][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:33:44,721][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:33:45,221][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:33:45,722][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:33:46,223][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:33:46,724][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:33:47,225][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:33:47,725][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:33:48,224][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:33:48,724][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:33:49,224][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:33:49,725][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:33:50,226][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:33:50,727][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:33:51,227][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:33:51,727][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:33:52,229][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:33:52,730][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:33:53,230][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:33:53,729][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:33:54,228][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:33:54,727][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:33:55,226][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:33:55,724][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:33:56,224][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:33:56,722][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:33:57,224][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:33:57,725][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:33:58,225][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:33:58,725][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:33:59,224][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:33:59,724][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:34:00,224][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:34:00,724][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:34:01,224][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:34:01,723][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:34:02,219][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:34:02,718][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:34:03,217][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:34:03,716][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:34:04,216][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:34:04,715][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:34:05,216][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:34:05,715][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:34:06,215][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:34:06,714][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:34:07,216][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:34:07,716][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:34:08,216][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:34:08,716][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:34:09,217][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:34:09,718][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:34:10,219][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:34:10,720][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:34:11,222][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:34:11,723][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:34:12,224][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:34:12,724][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:34:13,223][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:34:13,722][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:34:14,222][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:34:14,722][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:34:15,221][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:34:15,720][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:34:16,220][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:34:16,719][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:34:17,220][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:34:17,721][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:34:18,223][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:34:18,724][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:34:19,224][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:34:19,724][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:34:20,225][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:34:20,725][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:34:21,225][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:34:21,727][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:34:22,228][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:34:22,729][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:34:23,229][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:34:23,733][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:34:24,234][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:34:24,735][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 20:34:25,408][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.26%, ΔTime: 00:01:04 [2026-03-25 20:34:26,142][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:34:26,144][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:34:26,146][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:34:26,879][__main__][INFO] - Iteration 224 took 1m 14s (8.74% Gen, 90.27% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 56h 45m 36s. Estimated total time: 61h 44m 50s. Time estimates for 10 more iterations: 12m 20s, 100 more iterations: 2h 3m 29s, 500 more iterations: 10h 17m 28s. [2026-03-25 20:34:26,882][__main__][INFO] - Starting iteration 224. [2026-03-25 20:34:27,328][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:34:27,328][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:34:29,621][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:34:34,184][__main__][INFO] - Number of regex retries in iteration 224: 1 [2026-03-25 20:34:34,184][__main__][INFO] - agents played in iteration 224 are Bob, Alice [2026-03-25 20:34:35,165][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:34:35,774][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:34:36,238][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:34:36,752][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:34:37,258][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:34:37,769][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:34:38,276][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:34:38,784][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:34:39,294][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:34:39,801][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:34:40,308][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:34:40,814][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:34:41,320][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:34:41,825][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:34:42,327][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:34:42,835][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:34:43,340][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:34:43,846][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:34:44,355][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:34:44,861][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:34:45,370][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:34:45,878][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:34:46,386][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:34:46,896][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:34:47,402][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:34:47,913][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:34:48,424][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:34:48,933][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:34:49,442][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:34:49,949][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:34:50,459][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:34:50,967][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:34:51,475][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:34:51,985][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:34:52,497][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:34:53,005][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:34:53,516][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:34:54,024][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:34:54,533][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:34:55,044][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:34:55,551][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:34:56,061][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:34:56,570][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:34:57,076][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:34:57,586][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:34:58,095][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:34:58,604][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:34:59,114][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:34:59,622][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:35:00,130][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:35:00,640][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:35:01,146][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:35:01,655][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:35:02,163][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:35:02,669][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:35:03,178][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:35:03,684][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:35:04,190][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:35:04,698][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:35:05,206][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:35:05,714][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:35:06,220][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:35:06,729][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:35:07,239][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:35:07,747][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:35:08,254][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:35:08,763][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:35:09,271][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:35:09,778][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:35:10,284][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:35:10,791][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:35:11,300][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:35:11,809][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:35:12,317][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:35:12,821][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:35:13,326][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:35:13,830][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:35:14,335][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:35:14,838][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:35:15,345][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:35:15,852][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:35:16,357][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:35:16,864][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:35:17,375][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:35:17,884][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:35:18,394][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:35:18,901][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:35:19,409][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:35:19,920][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:35:20,430][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:35:20,937][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:35:21,447][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:35:21,958][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:35:22,468][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:35:22,977][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:35:23,489][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:35:24,000][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:35:24,509][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:35:25,021][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:35:25,532][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:35:26,041][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:35:26,553][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:35:27,062][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:35:27,570][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:35:28,079][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:35:28,589][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:35:29,098][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:35:29,608][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:35:30,119][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:35:30,628][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:35:31,134][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:35:31,644][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:35:32,153][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:35:32,662][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:35:33,170][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:35:33,679][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:35:34,186][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:35:34,694][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:35:35,202][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:35:35,712][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:35:36,222][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:35:36,729][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:35:37,239][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:35:37,748][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:35:38,255][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:35:38,764][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:35:39,273][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:35:39,781][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:35:40,289][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:35:40,799][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 20:35:41,490][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 20:35:42,271][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:35:42,273][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:35:42,275][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:35:43,000][__main__][INFO] - Iteration 225 took 1m 15s (9.06% Gen, 89.98% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 58h 3m 8s. Estimated total time: 63h 3m 38s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 7s, 500 more iterations: 10h 30m 36s. [2026-03-25 20:35:43,003][__main__][INFO] - Starting iteration 225. [2026-03-25 20:35:43,439][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:35:43,440][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:35:49,847][__main__][INFO] - Number of regex retries in iteration 225: 0 [2026-03-25 20:35:49,848][__main__][INFO] - agents played in iteration 225 are Bob, Alice [2026-03-25 20:35:50,826][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:35:51,459][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:35:51,925][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:35:52,438][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:35:52,947][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:35:53,458][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:35:53,968][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:35:54,479][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:35:54,987][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:35:55,497][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:35:56,010][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:35:56,523][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:35:57,032][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:35:57,542][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:35:58,052][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:35:58,561][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:35:59,072][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:35:59,585][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:36:00,094][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:36:00,603][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:36:01,114][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:36:01,625][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:36:02,133][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:36:02,642][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:36:03,154][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:36:03,664][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:36:04,172][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:36:04,682][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:36:05,193][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:36:05,702][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:36:06,213][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:36:06,724][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:36:07,233][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:36:07,742][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:36:08,254][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:36:08,764][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:36:09,272][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:36:09,782][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:36:10,292][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:36:10,800][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:36:11,309][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:36:11,820][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:36:12,330][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:36:12,837][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:36:13,347][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:36:13,858][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:36:14,368][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:36:14,874][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:36:15,382][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:36:15,891][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:36:16,425][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:36:16,935][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:36:17,445][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:36:17,954][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:36:18,460][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:36:18,968][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:36:19,476][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:36:19,983][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:36:20,490][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:36:20,999][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:36:21,508][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:36:22,016][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:36:22,524][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:36:23,034][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:36:23,545][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:36:24,052][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:36:24,561][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:36:25,071][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:36:25,579][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:36:26,086][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:36:26,596][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:36:27,105][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:36:27,614][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:36:28,122][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:36:28,633][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:36:29,143][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:36:29,653][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:36:30,161][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:36:30,671][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:36:31,181][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:36:31,691][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:36:32,201][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:36:32,711][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:36:33,222][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:36:33,731][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:36:34,239][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:36:34,749][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:36:35,259][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:36:35,770][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:36:36,277][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:36:36,786][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:36:37,297][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:36:37,806][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:36:38,314][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:36:38,824][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:36:39,334][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:36:39,841][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:36:40,352][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:36:40,863][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:36:41,371][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:36:41,879][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:36:42,385][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:36:42,894][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:36:43,402][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:36:43,909][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:36:44,416][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:36:44,924][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:36:45,430][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:36:45,959][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:36:46,475][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:36:46,981][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:36:47,487][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:36:48,001][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:36:48,517][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:36:49,036][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:36:49,544][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:36:50,072][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:36:50,581][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:36:51,099][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:36:51,612][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:36:52,120][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:36:52,631][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:36:53,137][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:36:53,642][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:36:54,147][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:36:54,653][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:36:55,160][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:36:55,665][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:36:56,171][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:36:56,677][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 20:36:57,356][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 20:36:58,109][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:36:58,111][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:36:58,113][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:36:58,814][__main__][INFO] - Iteration 226 took 1m 15s (8.50% Gen, 90.57% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 57h 47m 0s. Estimated total time: 62h 48m 46s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 37s, 500 more iterations: 10h 28m 7s. [2026-03-25 20:36:58,818][__main__][INFO] - Starting iteration 226. [2026-03-25 20:36:59,248][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:36:59,249][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:37:05,889][__main__][INFO] - Number of regex retries in iteration 226: 0 [2026-03-25 20:37:05,890][__main__][INFO] - agents played in iteration 226 are Bob, Alice [2026-03-25 20:37:06,827][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:37:07,446][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:37:07,911][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:37:08,425][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:37:08,936][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:37:09,446][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:37:09,956][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:37:10,465][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:37:10,974][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:37:11,482][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:37:11,989][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:37:12,494][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:37:12,998][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:37:13,519][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:37:14,008][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:37:14,518][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:37:15,024][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:37:15,530][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:37:16,035][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:37:16,541][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:37:17,048][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:37:17,554][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:37:18,060][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:37:18,567][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:37:19,074][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:37:19,581][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:37:20,088][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:37:20,595][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:37:21,102][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:37:21,609][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:37:22,116][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:37:22,624][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:37:23,139][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:37:23,664][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:37:24,174][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:37:24,680][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:37:25,186][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:37:25,691][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:37:26,200][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:37:26,705][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:37:27,214][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:37:27,720][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:37:28,226][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:37:28,734][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:37:29,244][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:37:29,750][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:37:30,294][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:37:30,800][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:37:31,311][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:37:33,292][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:37:33,857][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:37:34,366][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:37:34,872][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:37:35,448][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:37:36,000][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:37:36,523][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:37:37,055][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:37:37,563][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:37:38,130][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:37:38,638][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:37:39,145][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:37:39,665][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:37:40,170][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:37:40,681][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:37:41,185][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:37:41,696][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:37:42,206][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:37:42,732][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:37:43,279][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:37:43,791][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:37:44,285][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:37:44,794][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:37:45,304][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:37:45,816][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:37:46,323][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:37:46,830][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:37:47,366][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:37:47,873][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:37:48,406][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:37:48,912][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:37:49,429][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:37:49,934][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:37:50,441][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:37:50,948][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:37:51,454][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:37:51,960][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:37:52,466][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:37:53,000][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:37:53,521][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:37:54,029][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:37:54,535][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:37:55,043][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:37:55,550][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:37:56,057][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:37:56,576][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:37:57,070][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:37:57,579][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:37:58,087][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:37:58,594][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:37:59,101][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:37:59,608][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:38:00,116][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:38:00,624][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:38:01,132][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:38:01,638][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:38:02,147][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:38:02,657][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:38:03,168][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:38:03,679][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:38:04,186][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:38:04,692][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:38:05,198][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:38:05,705][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:38:06,212][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:38:06,720][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:38:07,230][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:38:07,737][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:38:08,245][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:38:08,751][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:38:09,260][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:38:09,767][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:38:10,278][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:38:10,786][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:38:11,293][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:38:11,800][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:38:12,308][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:38:12,826][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:38:13,335][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:38:13,849][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:38:14,372][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 20:38:15,155][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:07 [2026-03-25 20:38:15,843][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:38:15,845][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:38:15,847][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:38:26,508][__main__][INFO] - Iteration 227 took 1m 27s (7.61% Gen, 80.17% Train). Generation: 6s, Training: 1m 9s. Estimated remaining time: 67h 39m 48s. Estimated total time: 72h 43m 1s. Time estimates for 10 more iterations: 14m 32s, 100 more iterations: 2h 25m 26s, 500 more iterations: 12h 7m 10s. [2026-03-25 20:38:26,523][__main__][INFO] - Starting iteration 227. [2026-03-25 20:38:26,952][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:38:26,952][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:38:30,735][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:38:33,766][__main__][INFO] - Number of regex retries in iteration 227: 1 [2026-03-25 20:38:33,767][__main__][INFO] - agents played in iteration 227 are Bob, Alice [2026-03-25 20:38:34,790][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:38:35,687][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:38:36,156][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:38:36,672][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:38:37,175][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:38:37,677][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:38:38,180][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:38:38,684][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:38:39,189][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:38:39,692][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:38:40,201][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:38:40,709][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:38:41,220][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:38:41,729][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:38:42,235][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:38:42,751][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:38:43,259][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:38:43,774][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:38:44,285][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:38:44,793][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:38:45,302][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:38:45,810][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:38:46,317][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:38:46,834][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:38:47,346][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:38:47,864][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:38:48,371][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:38:48,887][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:38:49,395][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:38:49,907][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:38:50,416][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:38:50,942][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:38:51,454][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:38:51,963][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:38:52,490][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:38:53,003][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:38:53,516][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:38:54,027][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:38:54,536][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:38:55,045][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:38:55,561][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:38:56,085][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:38:56,614][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:38:57,127][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:38:57,636][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:38:58,144][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:38:58,654][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:38:59,175][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:38:59,683][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:39:00,190][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:39:00,695][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:39:01,201][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:39:01,705][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:39:02,212][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:39:02,719][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:39:03,231][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:39:03,738][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:39:04,245][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:39:04,752][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:39:05,271][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:39:05,797][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:39:06,304][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:39:06,810][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:39:07,316][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:39:07,821][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:39:08,326][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:39:08,827][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:39:09,333][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:39:09,836][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:39:10,342][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:39:10,844][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:39:11,353][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:39:11,856][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:39:12,359][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:39:12,864][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:39:13,370][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:39:13,875][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:39:14,381][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:39:14,888][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:39:15,393][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:39:15,899][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:39:16,407][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:39:16,915][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:39:17,429][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:39:17,936][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:39:18,444][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:39:18,959][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:39:19,466][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:39:19,976][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:39:20,497][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:39:21,004][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:39:21,511][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:39:22,017][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:39:22,525][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:39:23,031][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:39:23,537][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:39:24,044][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:39:24,593][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:39:25,076][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:39:25,583][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:39:26,090][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:39:26,606][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:39:27,116][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:39:27,627][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:39:28,135][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:39:28,643][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:39:29,151][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:39:29,659][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:39:30,167][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:39:30,681][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:39:31,189][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:39:31,703][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:39:32,209][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:39:32,717][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:39:33,223][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:39:33,738][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:39:34,259][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:39:34,765][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:39:35,279][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:39:35,788][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:39:36,321][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:39:36,833][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:39:37,343][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:39:37,853][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:39:38,357][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:39:38,861][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:39:39,366][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:39:39,883][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:39:40,388][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:39:40,892][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 20:39:41,563][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:05 [2026-03-25 20:39:42,327][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:39:42,330][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:39:42,331][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:39:43,036][__main__][INFO] - Iteration 228 took 1m 16s (8.96% Gen, 90.12% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 58h 19m 46s. Estimated total time: 63h 24m 16s. Time estimates for 10 more iterations: 12m 40s, 100 more iterations: 2h 6m 48s, 500 more iterations: 10h 34m 2s. [2026-03-25 20:39:43,039][__main__][INFO] - Starting iteration 228. [2026-03-25 20:39:43,454][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:39:43,455][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:39:46,795][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:39:50,292][__main__][INFO] - Number of regex retries in iteration 228: 1 [2026-03-25 20:39:50,293][__main__][INFO] - agents played in iteration 228 are Bob, Alice [2026-03-25 20:39:51,260][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:39:51,872][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:39:52,334][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:39:52,846][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:39:53,351][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:39:53,857][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:39:54,364][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:39:54,870][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:39:55,385][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:39:55,892][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:39:56,402][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:39:56,944][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:39:57,463][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:39:57,972][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:39:58,481][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:39:58,997][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:39:59,522][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:40:00,029][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:40:00,556][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:40:01,068][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:40:01,574][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:40:02,081][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:40:02,585][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:40:03,099][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:40:03,606][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:40:04,114][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:40:04,626][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:40:05,136][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:40:05,645][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:40:06,156][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:40:06,664][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:40:07,171][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:40:07,679][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:40:08,185][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:40:08,695][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:40:09,205][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:40:09,713][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:40:10,222][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:40:10,730][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:40:11,238][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:40:11,745][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:40:12,252][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:40:12,759][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:40:13,266][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:40:13,772][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:40:14,297][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:40:14,808][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:40:15,316][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:40:15,879][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:40:16,401][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:40:16,918][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:40:17,437][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:40:17,943][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:40:18,450][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:40:18,955][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:40:19,462][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:40:19,968][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:40:20,474][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:40:20,980][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:40:21,484][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:40:21,994][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:40:22,499][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:40:23,005][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:40:23,510][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:40:24,016][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:40:24,522][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:40:25,028][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:40:25,532][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:40:26,037][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:40:26,541][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:40:27,046][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:40:27,576][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:40:28,087][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:40:28,593][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:40:29,099][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:40:29,614][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:40:30,129][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:40:30,635][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:40:31,142][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:40:31,648][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:40:32,155][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:40:32,665][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:40:33,176][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:40:33,681][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:40:34,187][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:40:34,694][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:40:35,199][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:40:35,705][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:40:36,212][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:40:36,719][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:40:37,228][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:40:37,737][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:40:38,243][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:40:38,751][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:40:39,258][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:40:39,785][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:40:40,295][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:40:40,805][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:40:41,314][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:40:41,823][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:40:42,331][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:40:42,840][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:40:43,347][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:40:43,857][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:40:44,370][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:40:44,896][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:40:45,404][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:40:45,911][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:40:46,423][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:40:46,929][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:40:47,435][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:40:47,940][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:40:48,445][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:40:48,960][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:40:49,472][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:40:49,994][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:40:50,527][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:40:51,039][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:40:51,545][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:40:52,050][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:40:52,554][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:40:53,073][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:40:53,578][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:40:54,084][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:40:54,589][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:40:55,095][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:40:55,600][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:40:56,105][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:40:56,608][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:40:57,114][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 20:40:57,760][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 20:40:58,530][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:40:58,543][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:40:58,548][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:40:59,278][__main__][INFO] - Iteration 229 took 1m 15s (9.02% Gen, 90.02% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 58h 5m 25s. Estimated total time: 63h 11m 11s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 22s, 500 more iterations: 10h 31m 51s. [2026-03-25 20:40:59,280][__main__][INFO] - Starting iteration 229. [2026-03-25 20:40:59,692][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:40:59,702][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:41:03,914][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:41:06,896][__main__][INFO] - Number of regex retries in iteration 229: 1 [2026-03-25 20:41:06,897][__main__][INFO] - agents played in iteration 229 are Bob, Alice [2026-03-25 20:41:07,829][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:41:08,462][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:41:08,925][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:41:09,442][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:41:09,956][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:41:10,464][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:41:10,981][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:41:11,502][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:41:12,009][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:41:12,516][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:41:13,023][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:41:13,529][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:41:14,035][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:41:14,543][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:41:15,050][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:41:15,557][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:41:16,068][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:41:16,573][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:41:17,079][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:41:17,581][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:41:18,090][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:41:18,597][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:41:19,107][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:41:19,635][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:41:20,144][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:41:20,651][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:41:21,155][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:41:21,661][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:41:22,166][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:41:22,671][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:41:23,177][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:41:23,684][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:41:24,190][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:41:24,695][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:41:25,202][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:41:25,708][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:41:26,215][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:41:26,721][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:41:27,230][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:41:27,737][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:41:28,243][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:41:28,751][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:41:29,256][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:41:29,762][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:41:30,268][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:41:30,773][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:41:31,279][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:41:31,786][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:41:32,318][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:41:32,847][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:41:33,357][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:41:33,864][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:41:34,374][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:41:34,888][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:41:35,388][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:41:35,899][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:41:36,405][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:41:36,914][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:41:37,421][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:41:37,926][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:41:38,434][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:41:38,941][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:41:39,447][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:41:39,952][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:41:40,457][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:41:40,963][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:41:41,473][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:41:41,990][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:41:42,505][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:41:43,011][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:41:43,519][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:41:44,025][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:41:44,531][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:41:45,039][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:41:45,545][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:41:46,052][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:41:46,559][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:41:47,075][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:41:47,581][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:41:48,085][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:41:48,592][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:41:49,097][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:41:49,603][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:41:50,107][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:41:50,614][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:41:51,120][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:41:51,627][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:41:52,136][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:41:52,642][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:41:53,147][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:41:53,652][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:41:54,156][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:41:54,661][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:41:55,165][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:41:55,670][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:41:56,174][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:41:56,679][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:41:57,183][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:41:57,695][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:41:58,201][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:41:58,708][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:41:59,233][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:41:59,741][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:42:00,253][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:42:00,759][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:42:01,265][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:42:01,771][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:42:02,278][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:42:02,784][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:42:03,293][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:42:03,800][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:42:04,309][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:42:04,820][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:42:05,326][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:42:05,832][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:42:06,342][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:42:06,852][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:42:07,359][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:42:07,866][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:42:08,373][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:42:08,885][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:42:09,399][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:42:09,925][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:42:10,436][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:42:10,944][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:42:11,451][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:42:11,954][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:42:12,456][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:42:12,958][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:42:13,459][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21722 tokens. [2026-03-25 20:42:14,075][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:05 [2026-03-25 20:42:14,808][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:42:14,810][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:42:14,812][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:42:15,544][__main__][INFO] - Iteration 230 took 1m 15s (9.48% Gen, 89.53% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 58h 5m 38s. Estimated total time: 63h 12m 41s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 25s, 500 more iterations: 10h 32m 6s. [2026-03-25 20:42:15,546][__main__][INFO] - Starting iteration 230. [2026-03-25 20:42:15,945][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:42:15,945][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:42:22,713][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:42:23,771][__main__][INFO] - Number of regex retries in iteration 230: 1 [2026-03-25 20:42:23,772][__main__][INFO] - agents played in iteration 230 are Bob, Alice [2026-03-25 20:42:24,921][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:42:25,512][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:42:25,970][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:42:26,477][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:42:26,985][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:42:27,487][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:42:27,992][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:42:28,496][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:42:29,000][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:42:29,503][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:42:30,008][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:42:30,512][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:42:31,015][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:42:31,519][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:42:32,025][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:42:32,527][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:42:33,031][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:42:33,535][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:42:34,039][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:42:34,542][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:42:35,045][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:42:35,548][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:42:36,053][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:42:36,556][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:42:37,060][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:42:37,563][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:42:38,066][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:42:38,568][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:42:39,072][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:42:39,575][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:42:40,079][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:42:40,581][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:42:41,084][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:42:41,588][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:42:42,092][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:42:42,595][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:42:43,098][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:42:43,601][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:42:44,105][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:42:44,609][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:42:45,113][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:42:45,618][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:42:46,120][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:42:46,622][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:42:47,125][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:42:47,627][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:42:48,128][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:42:48,628][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:42:49,130][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:42:49,632][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:42:50,135][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:42:50,638][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:42:51,141][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:42:51,642][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:42:52,144][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:42:52,648][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:42:53,151][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:42:53,654][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:42:54,157][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:42:54,659][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:42:55,161][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:42:55,663][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:42:56,165][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:42:56,669][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:42:57,171][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:42:57,674][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:42:58,175][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:42:58,677][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:42:59,178][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:42:59,680][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:43:00,180][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:43:00,681][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:43:01,182][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:43:01,684][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:43:02,184][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:43:02,688][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:43:03,191][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:43:03,694][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:43:04,197][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:43:04,699][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:43:05,202][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:43:05,704][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:43:06,207][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:43:06,713][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:43:07,217][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:43:07,720][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:43:08,224][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:43:08,727][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:43:09,231][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:43:09,734][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:43:10,237][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:43:10,739][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:43:11,243][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:43:11,744][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:43:12,246][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:43:12,748][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:43:13,250][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:43:13,753][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:43:14,256][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:43:14,759][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:43:15,262][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:43:15,764][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:43:16,268][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:43:16,769][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:43:17,274][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:43:17,777][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:43:18,279][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:43:18,780][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:43:19,281][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:43:19,781][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:43:20,282][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:43:20,782][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:43:21,283][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:43:21,783][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:43:22,284][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:43:22,786][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:43:23,294][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:43:23,797][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:43:24,300][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:43:24,803][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:43:25,306][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:43:25,811][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:43:26,314][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:43:26,817][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:43:27,319][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:43:27,821][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:43:28,324][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:43:28,826][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:43:29,328][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:43:29,830][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 20:43:30,450][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-25 20:43:31,215][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:43:31,217][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:43:31,218][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:43:31,889][__main__][INFO] - Iteration 231 took 1m 15s (10.31% Gen, 88.81% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 58h 8m 56s. Estimated total time: 63h 17m 14s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 34s, 500 more iterations: 10h 32m 52s. [2026-03-25 20:43:31,891][__main__][INFO] - Starting iteration 231. [2026-03-25 20:43:32,301][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:43:32,302][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:43:39,734][__main__][INFO] - Number of regex retries in iteration 231: 0 [2026-03-25 20:43:39,735][__main__][INFO] - agents played in iteration 231 are Bob, Alice [2026-03-25 20:43:40,639][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:43:41,221][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:43:41,677][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:43:42,181][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:43:42,681][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:43:43,181][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:43:43,684][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:43:44,186][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:43:44,688][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:43:45,191][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:43:45,697][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:43:46,201][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:43:46,705][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:43:47,209][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:43:47,714][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:43:48,218][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:43:48,723][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:43:49,226][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:43:49,726][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:43:50,226][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:43:50,727][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:43:51,228][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:43:51,729][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:43:52,230][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:43:52,730][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:43:53,231][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:43:53,733][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:43:54,237][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:43:54,740][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:43:55,243][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:43:55,745][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:43:56,248][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:43:56,752][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:43:57,255][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:43:57,758][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:43:58,261][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:43:58,764][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:43:59,267][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:43:59,770][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:44:00,273][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:44:00,776][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:44:01,278][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:44:01,780][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:44:02,282][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:44:02,784][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:44:03,287][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:44:03,790][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:44:04,294][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:44:04,797][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:44:05,300][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:44:05,804][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:44:06,306][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:44:06,810][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:44:07,314][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:44:07,817][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:44:08,321][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:44:08,824][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:44:09,327][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:44:09,829][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:44:10,333][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:44:10,834][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:44:11,337][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:44:11,839][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:44:12,342][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:44:12,844][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:44:13,347][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:44:13,848][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:44:14,350][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:44:14,851][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:44:15,353][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:44:15,854][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:44:16,355][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:44:16,856][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:44:17,358][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:44:17,860][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:44:18,362][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:44:18,863][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:44:19,366][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:44:19,869][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:44:20,372][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:44:20,875][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:44:21,378][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:44:21,880][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:44:22,382][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:44:22,884][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:44:23,387][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:44:23,888][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:44:24,392][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:44:24,894][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:44:25,395][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:44:25,897][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:44:26,398][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:44:26,899][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:44:27,400][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:44:27,901][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:44:28,402][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:44:28,903][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:44:29,404][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:44:29,905][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:44:30,407][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:44:30,910][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:44:31,412][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:44:31,913][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:44:32,414][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:44:32,915][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:44:33,416][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:44:34,450][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:44:34,952][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:44:35,453][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:44:35,954][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:44:36,455][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:44:36,956][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:44:37,458][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:44:37,958][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:44:38,479][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:44:39,145][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:44:39,683][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:44:40,201][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:44:40,725][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:44:41,242][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:44:41,775][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:44:42,313][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:44:42,846][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:44:43,366][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:44:43,908][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:44:44,449][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:44:45,017][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:44:45,550][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:44:46,142][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:44:46,670][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 20:44:47,303][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:06 [2026-03-25 20:44:48,041][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:44:48,043][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:44:48,044][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:44:48,693][__main__][INFO] - Iteration 232 took 1m 16s (9.73% Gen, 89.42% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 58h 30m 1s. Estimated total time: 63h 39m 37s. Time estimates for 10 more iterations: 12m 43s, 100 more iterations: 2h 7m 19s, 500 more iterations: 10h 36m 36s. [2026-03-25 20:44:48,710][__main__][INFO] - Starting iteration 232. [2026-03-25 20:44:49,124][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:44:49,125][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:44:49,878][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:44:49,882][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:44:53,148][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 books, 10 hats, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:44:55,993][__main__][INFO] - Number of regex retries in iteration 232: 3 [2026-03-25 20:44:55,993][__main__][INFO] - agents played in iteration 232 are Bob, Alice [2026-03-25 20:44:57,250][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:44:57,846][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:44:58,374][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:44:58,889][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:44:59,403][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:44:59,917][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:45:00,423][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:45:00,937][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:45:01,476][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:45:02,008][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:45:02,541][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:45:03,059][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:45:03,570][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:45:04,100][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:45:04,627][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:45:05,179][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:45:05,700][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:45:06,224][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:45:06,749][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:45:07,297][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:45:07,830][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:45:08,363][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:45:09,015][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:45:09,540][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:45:10,054][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:45:10,558][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:45:11,058][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:45:11,560][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:45:12,061][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:45:12,561][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:45:13,120][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:45:13,629][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:45:14,159][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:45:14,675][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:45:15,184][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:45:15,718][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:45:16,236][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:45:16,784][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:45:17,378][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:45:17,945][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:45:18,469][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:45:19,004][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:45:19,508][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:45:20,037][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:45:20,547][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:45:21,073][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:45:21,581][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:45:22,096][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:45:22,652][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:45:23,157][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:45:23,687][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:45:24,201][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:45:24,717][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:45:25,235][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:45:25,823][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:45:26,364][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:45:26,883][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:45:27,390][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:45:28,167][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:45:28,740][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:45:29,242][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:45:29,744][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:45:30,245][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:45:30,745][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:45:31,246][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:45:31,781][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:45:32,294][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:45:32,847][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:45:33,392][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:45:33,935][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:45:34,461][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:45:34,999][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:45:35,542][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:45:36,104][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:45:36,645][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:45:37,186][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:45:37,776][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:45:38,334][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:45:38,910][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:45:39,454][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:45:39,984][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:45:40,521][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:45:41,036][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:45:41,569][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:45:42,093][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:45:42,605][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:45:43,127][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:45:43,633][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:45:44,147][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:45:44,672][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:45:45,178][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:45:45,684][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:45:46,207][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:45:46,724][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:45:47,236][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:45:47,867][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:45:48,367][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:45:48,868][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:45:49,366][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:45:49,865][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:45:50,363][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:45:50,897][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:45:51,419][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:45:51,946][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:45:52,461][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:45:52,980][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:45:53,500][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:45:54,033][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:45:54,578][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:45:55,114][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:45:55,637][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:45:56,185][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:45:56,710][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:45:57,248][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:45:57,773][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:45:58,319][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:45:58,853][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:45:59,379][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:45:59,984][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:46:00,506][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:46:01,022][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:46:01,564][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:46:02,092][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:46:02,612][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:46:03,134][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:46:03,651][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:46:04,185][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:46:04,711][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:46:05,249][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:46:05,763][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 20:46:06,425][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.28%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:08 [2026-03-25 20:46:07,162][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:46:07,164][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:46:07,166][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:46:07,875][__main__][INFO] - Iteration 233 took 1m 18s (8.72% Gen, 90.37% Train). Generation: 6s, Training: 1m 11s. Estimated remaining time: 60h 26m 43s. Estimated total time: 65h 37m 37s. Time estimates for 10 more iterations: 13m 7s, 100 more iterations: 2h 11m 15s, 500 more iterations: 10h 56m 16s. [2026-03-25 20:46:07,892][__main__][INFO] - Starting iteration 233. [2026-03-25 20:46:08,296][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:46:08,297][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:46:15,316][__main__][INFO] - Number of regex retries in iteration 233: 0 [2026-03-25 20:46:15,316][__main__][INFO] - agents played in iteration 233 are Bob, Alice [2026-03-25 20:46:16,331][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:46:16,917][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:46:17,453][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:46:17,968][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:46:18,468][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:46:18,984][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:46:19,506][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:46:20,007][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:46:20,511][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:46:21,034][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:46:21,604][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:46:22,141][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:46:22,686][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:46:23,418][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:46:23,912][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:46:24,434][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:46:24,972][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:46:25,503][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:46:26,050][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:46:26,606][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:46:27,118][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:46:27,618][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:46:28,118][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:46:28,617][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:46:29,117][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:46:29,617][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:46:30,135][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:46:30,686][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:46:31,352][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:46:31,889][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:46:32,480][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:46:33,041][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:46:33,605][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:46:34,164][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:46:34,708][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:46:35,235][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:46:35,776][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:46:36,314][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:46:36,845][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:46:37,423][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:46:37,958][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:46:38,515][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:46:39,058][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:46:39,570][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:46:40,142][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:46:40,705][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:46:41,221][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:46:41,761][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:46:42,321][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:46:42,865][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:46:43,497][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:46:44,043][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:46:44,573][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:46:45,117][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:46:45,639][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:46:46,150][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:46:46,651][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:46:47,152][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:46:47,653][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:46:48,172][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:46:48,724][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:46:49,236][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:46:49,790][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:46:50,327][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:46:50,890][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:46:51,409][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:46:51,968][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:46:52,559][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:46:53,135][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:46:53,659][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:46:54,178][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:46:54,734][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:46:55,266][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:46:55,815][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:46:56,392][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:46:56,992][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:46:57,533][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:46:58,072][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:46:58,664][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:46:59,215][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:46:59,802][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:47:00,302][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:47:00,801][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:47:01,300][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:47:01,799][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:47:02,298][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:47:02,797][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:47:03,296][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:47:04,633][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:47:05,146][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:47:05,651][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:47:06,156][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:47:06,661][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:47:07,164][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:47:07,669][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:47:08,175][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:47:08,679][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:47:09,182][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:47:09,684][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:47:10,190][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:47:10,696][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:47:11,201][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:47:11,706][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:47:12,212][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:47:12,717][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:47:13,223][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:47:13,727][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:47:14,232][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:47:14,737][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:47:15,241][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:47:15,745][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:47:16,249][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:47:16,755][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:47:17,259][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:47:17,765][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:47:18,269][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:47:18,776][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:47:19,282][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:47:19,788][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:47:20,296][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:47:20,802][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:47:21,308][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:47:21,815][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:47:22,321][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:47:22,826][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:47:23,333][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:47:23,839][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:47:24,345][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:47:24,851][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:47:25,357][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-25 20:47:26,092][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:09 [2026-03-25 20:47:26,805][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:47:26,808][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:47:26,809][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:47:27,490][__main__][INFO] - Iteration 234 took 1m 19s (8.86% Gen, 90.28% Train). Generation: 7s, Training: 1m 11s. Estimated remaining time: 60h 47m 29s. Estimated total time: 65h 59m 43s. Time estimates for 10 more iterations: 13m 11s, 100 more iterations: 2h 11m 59s, 500 more iterations: 10h 59m 57s. [2026-03-25 20:47:27,499][__main__][INFO] - Starting iteration 234. [2026-03-25 20:47:27,907][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:47:27,908][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:47:34,835][__main__][INFO] - Number of regex retries in iteration 234: 0 [2026-03-25 20:47:34,836][__main__][INFO] - agents played in iteration 234 are Bob, Alice [2026-03-25 20:47:35,851][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:47:36,751][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:47:37,215][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:47:37,724][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:47:38,231][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:47:38,738][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:47:39,244][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:47:39,750][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:47:40,257][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:47:40,763][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:47:41,273][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:47:41,781][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:47:42,289][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:47:42,797][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:47:43,304][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:47:43,811][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:47:44,319][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:47:44,827][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:47:45,333][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:47:45,839][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:47:46,345][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:47:46,853][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:47:47,359][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:47:47,865][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:47:48,370][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:47:48,876][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:47:49,382][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:47:49,887][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:47:50,394][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:47:50,900][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:47:51,406][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:47:51,912][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:47:52,418][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:47:52,923][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:47:53,435][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:47:53,946][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:47:54,457][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:47:54,967][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:47:55,477][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:47:55,987][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:47:56,497][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:47:57,006][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:47:57,513][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:47:58,019][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:47:58,529][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:47:59,036][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:47:59,543][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:48:00,049][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:48:00,554][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:48:01,061][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:48:01,567][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:48:02,074][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:48:02,579][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:48:03,085][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:48:03,592][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:48:04,100][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:48:04,606][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:48:05,115][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:48:05,623][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:48:06,130][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:48:06,638][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:48:07,145][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:48:07,654][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:48:08,161][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:48:08,668][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:48:09,177][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:48:09,683][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:48:10,187][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:48:10,693][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:48:11,199][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:48:11,704][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:48:12,209][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:48:12,715][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:48:13,220][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:48:13,727][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:48:14,235][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:48:14,743][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:48:15,249][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:48:15,757][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:48:16,265][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:48:16,772][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:48:17,278][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:48:17,783][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:48:18,288][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:48:18,794][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:48:19,299][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:48:19,804][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:48:20,310][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:48:20,816][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:48:21,321][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:48:21,826][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:48:22,333][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:48:22,839][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:48:23,344][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:48:23,849][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:48:24,354][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:48:24,860][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:48:25,366][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:48:25,876][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:48:26,383][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:48:26,895][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:48:27,405][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:48:27,914][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:48:28,424][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:48:28,934][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:48:29,444][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:48:29,949][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:48:30,456][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:48:30,962][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:48:31,468][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:48:31,973][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:48:32,478][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:48:32,984][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:48:33,489][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:48:33,995][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:48:34,501][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:48:35,006][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:48:35,513][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:48:36,019][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:48:36,526][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:48:37,035][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:48:37,541][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:48:38,049][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:48:38,556][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:48:39,064][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:48:39,571][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:48:40,078][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:48:40,584][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:48:41,091][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:48:41,598][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 20:48:42,252][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:05 [2026-03-25 20:48:42,972][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:48:42,974][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:48:42,976][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:48:43,664][__main__][INFO] - Iteration 235 took 1m 15s (9.14% Gen, 89.95% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 57h 54m 21s. Estimated total time: 63h 7m 51s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 15s, 500 more iterations: 10h 31m 18s. [2026-03-25 20:48:43,666][__main__][INFO] - Starting iteration 235. [2026-03-25 20:48:44,071][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:48:44,072][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:48:47,811][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:48:50,625][__main__][INFO] - Number of regex retries in iteration 235: 1 [2026-03-25 20:48:50,626][__main__][INFO] - agents played in iteration 235 are Bob, Alice [2026-03-25 20:48:51,611][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:48:52,231][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:48:52,695][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:48:53,207][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:48:53,715][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:48:54,223][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:48:54,731][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:48:55,239][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:48:55,746][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:48:56,253][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:48:56,759][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:48:57,265][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:48:57,773][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:48:58,280][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:48:58,785][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:48:59,295][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:48:59,802][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:49:00,308][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:49:00,816][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:49:01,323][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:49:01,829][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:49:02,336][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:49:02,844][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:49:03,350][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:49:03,857][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:49:04,364][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:49:04,870][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:49:05,376][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:49:05,882][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:49:06,388][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:49:06,894][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:49:07,399][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:49:07,905][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:49:08,412][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:49:08,919][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:49:09,425][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:49:09,934][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:49:10,441][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:49:10,947][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:49:11,453][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:49:11,960][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:49:12,466][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:49:12,972][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:49:13,477][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:49:13,982][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:49:14,488][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:49:14,995][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:49:15,501][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:49:16,006][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:49:16,515][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:49:17,026][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:49:17,533][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:49:18,040][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:49:18,548][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:49:19,057][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:49:19,564][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:49:20,069][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:49:20,577][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:49:21,085][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:49:21,592][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:49:22,101][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:49:22,609][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:49:23,117][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:49:23,625][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:49:24,133][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:49:24,641][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:49:25,149][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:49:25,657][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:49:26,163][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:49:26,671][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:49:27,178][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:49:27,686][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:49:28,194][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:49:28,702][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:49:29,209][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:49:29,717][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:49:30,224][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:49:30,731][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:49:31,238][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:49:31,745][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:49:32,251][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:49:32,758][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:49:33,266][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:49:33,772][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:49:34,279][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:49:34,786][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:49:35,294][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:49:35,800][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:49:36,307][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:49:36,817][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:49:37,324][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:49:37,830][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:49:38,336][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:49:38,843][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:49:39,349][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:49:39,855][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:49:40,360][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:49:40,866][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:49:41,373][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:49:41,879][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:49:42,386][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:49:42,894][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:49:43,400][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:49:43,907][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:49:44,414][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:49:44,921][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:49:45,429][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:49:45,936][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:49:46,445][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:49:46,952][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:49:47,460][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:49:47,968][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:49:48,476][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:49:48,983][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:49:49,492][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:49:50,000][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:49:50,507][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:49:51,017][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:49:51,525][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:49:52,033][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:49:52,542][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:49:53,049][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:49:53,557][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:49:54,065][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:49:54,573][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:49:55,080][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:49:55,588][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:49:56,096][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:49:56,604][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:49:57,115][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 20:49:57,782][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 20:49:58,511][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:49:58,513][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:49:58,515][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:49:59,336][__main__][INFO] - Iteration 236 took 1m 15s (8.71% Gen, 90.20% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 28m 30s. Estimated total time: 62h 43m 16s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 26s, 500 more iterations: 10h 27m 12s. [2026-03-25 20:49:59,338][__main__][INFO] - Starting iteration 236. [2026-03-25 20:49:59,740][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:49:59,741][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:50:00,361][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:50:06,593][__main__][INFO] - Number of regex retries in iteration 236: 1 [2026-03-25 20:50:06,594][__main__][INFO] - agents played in iteration 236 are Bob, Alice [2026-03-25 20:50:07,862][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:50:08,498][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:50:08,961][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:50:09,472][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:50:09,979][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:50:10,486][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:50:10,994][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:50:11,501][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:50:12,008][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:50:12,517][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:50:13,024][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:50:13,531][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:50:14,038][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:50:14,546][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:50:15,053][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:50:15,560][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:50:16,067][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:50:16,575][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:50:17,085][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:50:17,593][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:50:18,101][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:50:18,609][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:50:19,118][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:50:19,626][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:50:20,134][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:50:20,642][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:50:21,149][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:50:21,656][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:50:22,164][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:50:22,672][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:50:23,180][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:50:23,688][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:50:24,195][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:50:24,702][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:50:25,210][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:50:25,716][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:50:26,223][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:50:26,730][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:50:27,238][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:50:27,745][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:50:28,251][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:50:28,758][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:50:29,262][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:50:29,766][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:50:30,270][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:50:30,774][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:50:31,278][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:50:31,783][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:50:32,285][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:50:32,789][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:50:33,297][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:50:33,805][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:50:34,313][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:50:34,821][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:50:35,328][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:50:35,836][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:50:36,344][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:50:36,853][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:50:37,363][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:50:37,873][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:50:38,382][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:50:38,890][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:50:39,399][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:50:39,909][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:50:40,419][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:50:40,928][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:50:41,436][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:50:41,944][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:50:42,451][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:50:42,959][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:50:43,467][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:50:43,974][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:50:44,481][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:50:44,987][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:50:45,496][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:50:46,004][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:50:46,511][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:50:47,018][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:50:47,527][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:50:48,035][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:50:48,543][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:50:49,050][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:50:49,559][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:50:50,066][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:50:50,574][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:50:51,083][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:50:51,590][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:50:52,098][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:50:52,606][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:50:53,117][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:50:53,625][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:50:54,133][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:50:54,641][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:50:55,149][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:50:55,657][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:50:56,166][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:50:56,673][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:50:57,182][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:50:57,689][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:50:58,197][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:50:58,704][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:50:59,212][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:50:59,720][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:51:00,226][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:51:00,734][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:51:01,241][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:51:01,746][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:51:02,249][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:51:02,753][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:51:03,259][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:51:03,763][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:51:04,267][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:51:04,770][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:51:05,273][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:51:05,779][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:51:06,286][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:51:06,793][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:51:07,301][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:51:07,809][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:51:08,317][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:51:08,826][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:51:09,333][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:51:09,841][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:51:10,351][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:51:10,859][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:51:11,368][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:51:11,877][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:51:12,388][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:51:12,896][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:51:13,404][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21746 tokens. [2026-03-25 20:51:14,094][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 20:51:14,824][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:51:14,827][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:51:14,828][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:51:15,627][__main__][INFO] - Iteration 237 took 1m 15s (9.03% Gen, 89.91% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 57h 58m 20s. Estimated total time: 63h 14m 22s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 28s, 500 more iterations: 10h 32m 23s. [2026-03-25 20:51:15,629][__main__][INFO] - Starting iteration 237. [2026-03-25 20:51:16,033][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:51:16,034][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:51:22,219][__main__][INFO] - Number of regex retries in iteration 237: 0 [2026-03-25 20:51:22,220][__main__][INFO] - agents played in iteration 237 are Bob, Alice [2026-03-25 20:51:23,489][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:51:24,133][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:51:24,593][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:51:25,104][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:51:25,609][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:51:26,115][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:51:26,621][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:51:27,127][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:51:27,633][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:51:28,140][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:51:28,650][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:51:29,157][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:51:29,664][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:51:30,171][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:51:30,678][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:51:31,186][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:51:31,694][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:51:32,201][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:51:32,709][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:51:33,216][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:51:33,724][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:51:34,233][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:51:34,740][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:51:35,247][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:51:35,755][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:51:36,264][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:51:36,773][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:51:37,282][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:51:37,791][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:51:38,299][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:51:38,807][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:51:39,317][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:51:39,827][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:51:40,336][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:51:40,844][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:51:41,352][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:51:41,859][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:51:42,366][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:51:42,873][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:51:43,381][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:51:43,889][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:51:44,398][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:51:44,905][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:51:45,414][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:51:45,922][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:51:46,430][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:51:46,937][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:51:47,445][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:51:47,953][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:51:48,460][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:51:48,968][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:51:49,476][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:51:49,984][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:51:50,493][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:51:51,002][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:51:51,511][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:51:52,019][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:51:52,527][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:51:53,037][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:51:53,546][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:51:54,055][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:51:54,564][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:51:55,073][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:51:55,581][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:51:56,088][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:51:56,597][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:51:57,103][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:51:57,611][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:51:58,117][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:51:58,625][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:51:59,131][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:51:59,639][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:52:00,146][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:52:00,651][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:52:01,161][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:52:01,669][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:52:02,178][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:52:02,684][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:52:03,194][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:52:03,702][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:52:04,211][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:52:04,718][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:52:05,227][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:52:05,736][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:52:06,244][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:52:06,749][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:52:07,255][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:52:07,763][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:52:08,271][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:52:08,779][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:52:09,287][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:52:09,796][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:52:10,305][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:52:10,817][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:52:11,327][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:52:11,836][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:52:12,345][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:52:12,855][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:52:13,363][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:52:13,872][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:52:14,379][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:52:14,888][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:52:15,396][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:52:15,903][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:52:16,412][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:52:16,921][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:52:17,429][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:52:17,937][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:52:18,445][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:52:18,954][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:52:19,462][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:52:19,970][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:52:20,479][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:52:20,988][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:52:21,497][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:52:22,005][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:52:22,515][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:52:23,024][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:52:23,533][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:52:24,042][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:52:24,551][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:52:25,060][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:52:25,567][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:52:26,077][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:52:26,585][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:52:27,093][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:52:27,602][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:52:28,110][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:52:28,620][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:52:29,129][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 20:52:29,807][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-25 20:52:30,534][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:52:30,536][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:52:30,538][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:52:31,184][__main__][INFO] - Iteration 238 took 1m 15s (8.23% Gen, 90.91% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 57h 20m 16s. Estimated total time: 62h 37m 33s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 15s, 500 more iterations: 10h 26m 15s. [2026-03-25 20:52:31,186][__main__][INFO] - Starting iteration 238. [2026-03-25 20:52:31,587][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:52:31,588][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:52:34,195][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:52:38,051][__main__][INFO] - Number of regex retries in iteration 238: 1 [2026-03-25 20:52:38,052][__main__][INFO] - agents played in iteration 238 are Bob, Alice [2026-03-25 20:52:39,018][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:52:39,667][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:52:40,133][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:52:40,647][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:52:41,156][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:52:41,666][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:52:42,176][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:52:42,686][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:52:43,197][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:52:43,706][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:52:44,216][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:52:44,724][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:52:45,233][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:52:45,742][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:52:46,251][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:52:46,759][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:52:47,267][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:52:47,778][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:52:48,288][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:52:48,797][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:52:49,305][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:52:49,816][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:52:50,324][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:52:50,832][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:52:51,341][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:52:51,850][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:52:52,357][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:52:52,865][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:52:53,375][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:52:53,883][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:52:54,391][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:52:54,900][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:52:55,408][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:52:55,916][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:52:56,426][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:52:56,935][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:52:57,443][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:52:57,952][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:52:58,459][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:52:58,967][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:52:59,476][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:52:59,985][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:53:00,493][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:53:01,002][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:53:01,511][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:53:02,019][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:53:02,527][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:53:03,037][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:53:03,546][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:53:04,053][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:53:04,561][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:53:05,068][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:53:05,576][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:53:06,083][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:53:06,590][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:53:07,098][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:53:07,607][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:53:08,114][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:53:08,622][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:53:09,130][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:53:09,639][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:53:10,147][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:53:10,655][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:53:11,164][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:53:11,671][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:53:12,179][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:53:12,687][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:53:13,196][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:53:13,704][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:53:14,213][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:53:14,721][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:53:15,230][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:53:15,738][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:53:16,247][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:53:16,755][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:53:17,263][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:53:17,771][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:53:18,279][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:53:18,787][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:53:19,295][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:53:19,802][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:53:20,310][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:53:20,818][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:53:21,327][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:53:21,835][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:53:22,343][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:53:22,852][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:53:23,359][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:53:23,867][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:53:24,375][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:53:24,882][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:53:25,389][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:53:25,896][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:53:26,403][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:53:26,910][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:53:27,417][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:53:27,924][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:53:28,431][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:53:28,940][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:53:29,448][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:53:29,955][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:53:30,462][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:53:30,970][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:53:31,477][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:53:31,985][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:53:32,494][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:53:33,001][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:53:33,509][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:53:34,017][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:53:34,525][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:53:35,033][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:53:35,541][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:53:36,049][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:53:36,555][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:53:37,062][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:53:37,568][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:53:38,076][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:53:38,581][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:53:39,088][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:53:39,595][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:53:40,101][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:53:40,606][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:53:41,115][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:53:41,622][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:53:42,130][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:53:42,637][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:53:43,144][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:53:43,653][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:53:44,160][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:53:44,667][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21760 tokens. [2026-03-25 20:53:45,323][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-25 20:53:46,049][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:53:46,052][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:53:46,054][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:53:46,803][__main__][INFO] - Iteration 239 took 1m 15s (8.59% Gen, 90.41% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 57h 22m 16s. Estimated total time: 62h 40m 50s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 21s, 500 more iterations: 10h 26m 48s. [2026-03-25 20:53:46,806][__main__][INFO] - Starting iteration 239. [2026-03-25 20:53:47,206][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:53:47,207][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:53:47,836][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:53:54,291][__main__][INFO] - Number of regex retries in iteration 239: 1 [2026-03-25 20:53:54,292][__main__][INFO] - agents played in iteration 239 are Bob, Alice [2026-03-25 20:53:55,269][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:53:55,907][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:53:56,372][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:53:56,883][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:53:57,389][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:53:57,898][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:53:58,405][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:53:58,912][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:53:59,421][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:53:59,929][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:54:00,436][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:54:00,944][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:54:01,450][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:54:01,958][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:54:02,464][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:54:02,970][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:54:03,476][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:54:03,983][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:54:04,490][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:54:04,998][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:54:05,505][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:54:06,012][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:54:06,519][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:54:07,026][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:54:07,532][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:54:08,040][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:54:08,547][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:54:09,055][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:54:09,562][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:54:10,071][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:54:10,576][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:54:11,083][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:54:11,590][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:54:12,097][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:54:12,605][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:54:13,113][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:54:13,620][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:54:14,128][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:54:14,636][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:54:15,142][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:54:15,650][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:54:16,157][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:54:16,666][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:54:17,175][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:54:17,684][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:54:18,191][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:54:18,699][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:54:19,208][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:54:19,716][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:54:20,224][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:54:20,732][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:54:21,238][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:54:21,745][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:54:22,252][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:54:22,758][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:54:23,264][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:54:23,771][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:54:24,279][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:54:24,784][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:54:25,292][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:54:25,800][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:54:26,307][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:54:26,815][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:54:27,323][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:54:27,830][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:54:28,338][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:54:28,845][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:54:29,354][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:54:29,861][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:54:30,370][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:54:30,877][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:54:31,384][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:54:31,891][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:54:32,399][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:54:32,905][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:54:33,413][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:54:33,920][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:54:34,426][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:54:34,933][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:54:35,439][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:54:35,946][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:54:36,453][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:54:36,959][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:54:37,466][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:54:37,974][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:54:38,480][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:54:38,987][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:54:39,494][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:54:40,001][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:54:40,508][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:54:41,016][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:54:41,523][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:54:42,030][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:54:42,536][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:54:43,044][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:54:43,550][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:54:44,057][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:54:44,564][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:54:45,070][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:54:45,577][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:54:46,084][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:54:46,591][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:54:47,099][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:54:47,606][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:54:48,114][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:54:48,622][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:54:49,130][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:54:49,637][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:54:50,145][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:54:50,653][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:54:51,160][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:54:51,667][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:54:52,176][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:54:52,684][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:54:53,190][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:54:53,696][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:54:54,203][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:54:54,710][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:54:55,217][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:54:55,725][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:54:56,232][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:54:56,739][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:54:57,246][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:54:57,753][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:54:58,261][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:54:58,768][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:54:59,274][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:54:59,780][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:55:00,287][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:55:00,794][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21694 tokens. [2026-03-25 20:55:01,458][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 20:55:02,189][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:55:02,191][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:55:02,193][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:55:02,897][__main__][INFO] - Iteration 240 took 1m 15s (9.36% Gen, 89.71% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 57h 44m 44s. Estimated total time: 63h 4m 33s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 9s, 500 more iterations: 10h 30m 45s. [2026-03-25 20:55:02,899][__main__][INFO] - Starting iteration 240. [2026-03-25 20:55:03,301][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:55:03,302][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:55:10,048][__main__][INFO] - Number of regex retries in iteration 240: 0 [2026-03-25 20:55:10,049][__main__][INFO] - agents played in iteration 240 are Bob, Alice [2026-03-25 20:55:11,020][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:55:11,651][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:55:12,114][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:55:12,626][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:55:13,134][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:55:13,641][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:55:14,149][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:55:14,656][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:55:15,164][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:55:15,671][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:55:16,180][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:55:16,687][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:55:17,194][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:55:17,701][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:55:18,207][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:55:18,714][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:55:19,221][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:55:19,728][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:55:20,237][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:55:20,746][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:55:21,255][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:55:21,763][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:55:22,271][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:55:22,779][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:55:23,287][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:55:23,796][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:55:24,304][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:55:24,813][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:55:25,322][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:55:25,830][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:55:26,338][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:55:26,846][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:55:27,353][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:55:27,861][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:55:28,368][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:55:28,874][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:55:29,381][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:55:29,888][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:55:30,396][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:55:30,903][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:55:31,410][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:55:31,918][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:55:32,425][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:55:32,933][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:55:33,440][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:55:33,947][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:55:34,455][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:55:34,962][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:55:35,469][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:55:35,977][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:55:36,484][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:55:36,992][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:55:37,499][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:55:38,006][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:55:38,514][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:55:39,021][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:55:39,528][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:55:40,036][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:55:40,544][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:55:41,052][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:55:41,559][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:55:42,067][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:55:42,575][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:55:43,082][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:55:43,590][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:55:44,097][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:55:44,604][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:55:45,111][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:55:45,618][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:55:46,125][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:55:46,632][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:55:47,139][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:55:47,646][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:55:48,152][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:55:48,659][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:55:49,167][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:55:49,674][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:55:50,181][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:55:50,688][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:55:51,196][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:55:51,704][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:55:52,211][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:55:52,720][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:55:53,228][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:55:53,736][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:55:54,244][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:55:54,753][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:55:55,262][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:55:55,771][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:55:56,279][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:55:56,786][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:55:57,293][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:55:57,800][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:55:58,307][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:55:58,815][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:55:59,322][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:55:59,830][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:56:00,337][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:56:00,843][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:56:01,350][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:56:01,857][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:56:02,364][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:56:02,872][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:56:03,378][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:56:03,884][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:56:04,391][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:56:04,897][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:56:05,405][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:56:05,912][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:56:06,420][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:56:06,927][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:56:07,436][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:56:07,944][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:56:08,450][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:56:08,958][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:56:09,466][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:56:09,973][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:56:10,480][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:56:10,987][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:56:11,494][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:56:12,001][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:56:12,509][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:56:13,018][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:56:13,527][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:56:14,034][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:56:14,542][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:56:15,050][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:56:15,558][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:56:16,067][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:56:16,573][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21737 tokens. [2026-03-25 20:56:17,223][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:05 [2026-03-25 20:56:17,962][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:56:17,965][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:56:17,966][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:56:18,624][__main__][INFO] - Iteration 241 took 1m 15s (8.96% Gen, 90.17% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 25m 5s. Estimated total time: 62h 46m 10s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 32s, 500 more iterations: 10h 27m 41s. [2026-03-25 20:56:18,626][__main__][INFO] - Starting iteration 241. [2026-03-25 20:56:19,028][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:56:19,028][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:56:23,841][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:56:26,080][__main__][INFO] - Number of regex retries in iteration 241: 1 [2026-03-25 20:56:26,081][__main__][INFO] - agents played in iteration 241 are Bob, Alice [2026-03-25 20:56:27,041][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:56:27,671][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:56:28,136][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:56:28,649][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:56:29,157][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:56:29,665][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:56:30,174][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:56:30,682][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:56:31,190][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:56:31,698][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:56:32,204][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:56:32,711][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:56:33,217][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:56:33,724][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:56:34,231][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:56:34,737][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:56:35,244][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:56:35,749][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:56:36,258][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:56:36,765][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:56:37,273][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:56:37,781][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:56:38,287][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:56:38,794][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:56:39,301][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:56:39,807][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:56:40,317][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:56:40,825][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:56:41,332][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:56:41,842][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:56:42,351][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:56:42,859][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:56:43,365][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:56:43,872][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:56:44,378][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:56:44,886][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:56:45,394][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:56:45,901][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:56:46,409][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:56:46,916][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:56:47,423][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:56:47,930][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:56:48,437][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:56:48,942][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:56:49,449][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:56:49,955][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:56:50,461][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:56:50,967][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:56:51,473][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:56:51,979][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:56:52,485][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:56:52,994][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:56:53,501][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:56:54,008][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:56:54,517][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:56:55,025][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:56:55,534][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:56:56,041][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:56:56,547][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:56:57,055][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:56:57,562][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:56:58,069][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:56:58,576][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:56:59,083][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:56:59,590][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:57:00,098][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:57:00,605][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:57:01,114][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:57:01,622][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:57:02,131][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:57:02,639][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:57:03,146][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:57:03,654][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:57:04,161][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:57:04,668][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:57:05,174][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:57:05,680][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:57:06,186][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:57:06,693][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:57:07,199][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:57:07,705][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:57:08,211][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:57:08,718][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:57:09,226][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:57:09,734][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:57:10,242][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:57:10,748][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:57:11,256][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:57:11,763][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:57:12,270][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:57:12,777][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:57:13,284][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:57:13,792][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:57:14,299][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:57:14,806][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:57:15,316][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:57:15,825][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:57:16,332][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:57:16,840][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:57:17,346][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:57:17,854][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:57:18,361][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:57:18,869][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:57:19,377][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:57:19,884][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:57:20,391][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:57:20,898][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:57:21,404][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:57:21,911][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:57:22,418][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:57:22,925][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:57:23,431][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:57:23,937][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:57:24,444][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:57:24,951][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:57:25,459][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:57:25,966][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:57:26,473][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:57:26,980][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:57:27,488][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:57:27,996][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:57:28,504][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:57:29,010][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:57:29,517][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:57:30,023][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:57:30,530][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:57:31,036][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:57:31,543][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:57:32,050][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:57:32,557][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-25 20:57:33,208][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 20:57:33,958][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:57:33,960][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:57:33,962][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:57:34,623][__main__][INFO] - Iteration 242 took 1m 15s (9.33% Gen, 89.79% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 57h 37m 26s. Estimated total time: 62h 59m 48s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 59s, 500 more iterations: 10h 29m 58s. [2026-03-25 20:57:34,625][__main__][INFO] - Starting iteration 242. [2026-03-25 20:57:35,027][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:57:35,028][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:57:35,654][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:57:36,310][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 20:57:42,159][__main__][INFO] - Number of regex retries in iteration 242: 2 [2026-03-25 20:57:42,160][__main__][INFO] - agents played in iteration 242 are Bob, Alice [2026-03-25 20:57:43,126][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:57:43,753][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:57:44,216][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:57:44,728][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:57:45,235][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:57:45,743][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:57:46,250][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:57:46,756][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:57:47,263][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:57:47,770][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:57:48,277][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:57:48,784][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:57:49,290][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:57:49,797][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:57:50,304][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:57:50,812][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:57:51,319][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:57:51,827][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:57:52,337][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:57:52,845][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:57:53,353][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:57:53,860][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:57:54,367][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:57:54,875][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:57:55,384][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:57:55,892][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:57:56,398][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:57:56,904][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:57:57,411][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:57:57,918][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:57:58,424][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:57:58,930][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:57:59,436][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:57:59,942][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:58:00,448][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:58:00,955][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:58:01,462][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:58:01,968][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:58:02,474][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:58:02,980][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:58:03,486][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:58:03,992][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:58:04,499][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:58:05,007][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:58:05,515][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:58:06,023][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:58:06,530][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:58:07,038][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:58:07,546][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:58:08,054][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:58:08,560][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:58:09,067][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:58:09,574][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:58:10,081][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:58:10,589][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:58:11,096][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:58:11,603][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:58:12,111][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:58:12,619][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:58:13,126][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:58:13,634][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:58:14,142][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:58:14,649][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:58:15,156][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:58:15,664][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:58:16,172][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:58:16,679][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:58:17,186][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:58:17,694][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:58:18,201][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:58:18,708][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:58:19,216][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:58:19,723][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:58:20,230][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:58:20,736][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:58:21,244][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:58:21,751][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:58:22,258][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:58:22,762][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:58:23,269][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:58:23,773][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:58:24,281][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:58:24,789][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:58:25,297][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:58:25,805][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:58:26,314][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:58:26,822][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:58:27,329][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:58:27,838][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:58:28,346][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:58:28,853][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:58:29,360][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:58:29,866][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:58:30,373][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:58:30,880][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:58:31,386][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:58:31,896][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:58:32,403][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:58:32,910][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:58:33,418][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:58:33,924][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:58:34,431][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:58:34,937][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:58:35,443][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:58:35,950][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:58:36,456][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:58:36,963][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:58:37,470][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:58:37,978][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:58:38,484][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:58:38,992][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:58:39,498][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:58:40,006][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:58:40,514][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:58:41,021][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:58:41,528][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:58:42,036][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:58:42,544][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:58:43,051][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:58:43,558][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:58:44,064][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 20:58:44,572][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 20:58:45,079][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 20:58:45,586][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 20:58:46,093][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 20:58:46,601][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 20:58:47,108][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 20:58:47,616][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 20:58:48,123][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 20:58:48,631][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21714 tokens. [2026-03-25 20:58:49,294][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 20:58:50,028][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 20:58:50,030][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 20:58:50,032][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 20:58:50,691][__main__][INFO] - Iteration 243 took 1m 15s (9.43% Gen, 89.70% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 57h 39m 36s. Estimated total time: 63h 3m 13s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 6s, 500 more iterations: 10h 30m 32s. [2026-03-25 20:58:50,693][__main__][INFO] - Starting iteration 243. [2026-03-25 20:58:51,094][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 20:58:51,094][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 20:58:57,899][__main__][INFO] - Number of regex retries in iteration 243: 0 [2026-03-25 20:58:57,900][__main__][INFO] - agents played in iteration 243 are Bob, Alice [2026-03-25 20:58:58,871][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 20:58:59,501][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 20:58:59,965][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 20:59:00,477][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 20:59:00,985][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 20:59:01,491][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 20:59:01,999][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 20:59:02,507][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 20:59:03,015][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 20:59:03,522][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 20:59:04,031][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 20:59:04,539][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 20:59:05,046][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 20:59:05,552][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 20:59:06,059][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 20:59:06,565][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 20:59:07,071][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 20:59:07,578][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 20:59:08,085][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 20:59:08,591][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 20:59:09,098][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 20:59:09,604][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 20:59:10,110][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 20:59:10,616][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 20:59:11,123][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 20:59:11,629][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 20:59:12,136][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 20:59:12,643][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 20:59:13,150][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 20:59:13,656][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 20:59:14,163][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 20:59:14,669][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 20:59:15,176][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 20:59:15,683][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 20:59:16,192][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 20:59:16,700][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 20:59:17,208][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 20:59:17,716][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 20:59:18,224][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 20:59:18,732][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 20:59:19,240][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 20:59:19,748][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 20:59:20,274][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 20:59:20,786][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 20:59:21,294][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 20:59:21,802][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 20:59:22,310][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 20:59:22,820][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 20:59:23,328][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 20:59:23,836][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 20:59:24,343][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 20:59:24,850][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 20:59:25,356][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 20:59:25,862][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 20:59:26,369][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 20:59:26,875][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 20:59:27,381][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 20:59:27,887][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 20:59:28,397][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 20:59:28,905][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 20:59:29,414][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 20:59:29,922][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 20:59:30,431][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 20:59:30,939][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 20:59:31,447][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 20:59:31,956][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 20:59:32,464][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 20:59:32,970][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 20:59:33,476][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 20:59:33,983][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 20:59:34,490][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 20:59:34,996][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 20:59:35,503][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 20:59:36,010][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 20:59:36,517][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 20:59:37,025][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 20:59:37,532][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 20:59:38,040][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 20:59:38,548][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 20:59:39,056][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 20:59:39,564][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 20:59:40,071][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 20:59:40,577][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 20:59:41,084][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 20:59:41,590][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 20:59:42,096][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 20:59:42,603][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 20:59:43,110][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 20:59:43,617][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 20:59:44,125][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 20:59:44,633][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 20:59:45,139][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 20:59:45,646][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 20:59:46,152][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 20:59:46,659][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 20:59:47,165][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 20:59:47,671][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 20:59:48,177][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 20:59:48,685][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 20:59:49,194][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 20:59:49,702][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 20:59:50,209][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 20:59:50,718][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 20:59:51,227][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 20:59:51,734][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 20:59:52,243][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 20:59:52,750][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 20:59:53,258][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 20:59:53,766][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 20:59:54,274][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 20:59:54,782][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 20:59:55,290][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 20:59:55,798][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 20:59:56,306][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 20:59:56,814][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 20:59:57,320][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 20:59:57,826][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 20:59:58,332][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 20:59:58,838][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 20:59:59,343][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 20:59:59,849][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:00:00,356][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:00:00,864][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:00:01,372][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:00:01,880][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:00:02,387][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:00:02,898][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:00:03,407][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:00:03,915][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:00:04,424][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21734 tokens. [2026-03-25 21:00:05,077][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.28%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:05 [2026-03-25 21:00:05,815][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:00:05,818][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:00:05,819][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:00:06,503][__main__][INFO] - Iteration 244 took 1m 15s (9.02% Gen, 90.07% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 25m 37s. Estimated total time: 62h 50m 31s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 41s, 500 more iterations: 10h 28m 25s. [2026-03-25 21:00:06,505][__main__][INFO] - Starting iteration 244. [2026-03-25 21:00:06,907][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 21:00:06,908][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:00:13,533][__main__][INFO] - Number of regex retries in iteration 244: 0 [2026-03-25 21:00:13,534][__main__][INFO] - agents played in iteration 244 are Bob, Alice [2026-03-25 21:00:14,506][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:00:15,126][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:00:15,590][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:00:16,103][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:00:16,611][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:00:17,119][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:00:17,628][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:00:18,136][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:00:18,643][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:00:19,151][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:00:19,657][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:00:20,163][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:00:20,670][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:00:21,176][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:00:21,683][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:00:22,189][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:00:22,696][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:00:23,203][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:00:23,711][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:00:24,218][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:00:24,725][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:00:25,232][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:00:25,739][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:00:26,246][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:00:26,753][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:00:27,259][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:00:27,765][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:00:28,270][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:00:28,776][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:00:29,281][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:00:29,785][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:00:30,291][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:00:30,796][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:00:31,302][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:00:31,807][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:00:32,314][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:00:32,820][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:00:33,326][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:00:33,835][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:00:34,342][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:00:34,848][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:00:35,354][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:00:35,860][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:00:36,365][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:00:36,870][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:00:37,377][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:00:37,883][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:00:38,388][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:00:38,895][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:00:39,400][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:00:39,906][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:00:40,415][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:00:40,923][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:00:41,430][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:00:41,937][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:00:42,444][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:00:42,951][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:00:43,458][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:00:43,966][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:00:44,474][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:00:44,982][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:00:45,488][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:00:45,995][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:00:46,502][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:00:47,010][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:00:47,516][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:00:48,025][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:00:48,535][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:00:49,044][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:00:49,551][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:00:50,059][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:00:50,567][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:00:51,075][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:00:51,582][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:00:52,088][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:00:52,597][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:00:53,104][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:00:53,610][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:00:54,118][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:00:54,625][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:00:55,131][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:00:55,639][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:00:56,145][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:00:56,653][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:00:57,160][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:00:57,666][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:00:58,173][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:00:58,679][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:00:59,185][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:00:59,691][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:01:00,198][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:01:00,704][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:01:01,210][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:01:01,716][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:01:02,224][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:01:02,729][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:01:03,237][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:01:03,745][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:01:04,250][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:01:04,757][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:01:05,263][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:01:05,769][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:01:06,275][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:01:06,781][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:01:07,286][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:01:07,790][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:01:08,294][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:01:08,799][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:01:09,305][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:01:09,813][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:01:10,321][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:01:10,828][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:01:11,334][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:01:11,841][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:01:12,348][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:01:12,856][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:01:13,363][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:01:13,870][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:01:14,376][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:01:14,883][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:01:15,390][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:01:15,897][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:01:16,404][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:01:16,911][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:01:17,419][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:01:17,926][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:01:18,434][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:01:18,941][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:01:19,448][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:01:19,956][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 21:01:20,608][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-25 21:01:21,347][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:01:21,350][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:01:21,351][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:01:22,296][__main__][INFO] - Iteration 245 took 1m 15s (8.79% Gen, 89.96% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 23m 18s. Estimated total time: 62h 49m 27s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 38s, 500 more iterations: 10h 28m 14s. [2026-03-25 21:01:22,298][__main__][INFO] - Starting iteration 245. [2026-03-25 21:01:22,701][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 21:01:22,701][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:01:28,824][__main__][INFO] - Number of regex retries in iteration 245: 0 [2026-03-25 21:01:28,826][__main__][INFO] - agents played in iteration 245 are Bob, Alice [2026-03-25 21:01:30,081][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:01:30,705][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:01:31,168][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:01:31,678][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:01:32,184][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:01:32,690][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:01:33,196][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:01:33,703][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:01:34,209][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:01:34,717][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:01:35,226][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:01:35,734][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:01:36,241][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:01:36,747][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:01:37,256][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:01:37,763][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:01:38,270][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:01:38,776][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:01:39,286][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:01:39,793][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:01:40,301][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:01:40,806][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:01:41,317][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:01:41,824][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:01:42,333][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:01:42,840][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:01:43,348][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:01:43,855][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:01:44,362][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:01:44,870][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:01:45,377][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:01:45,886][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:01:46,392][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:01:46,900][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:01:47,407][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:01:47,915][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:01:48,424][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:01:48,931][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:01:49,439][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:01:49,946][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:01:50,456][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:01:50,963][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:01:51,471][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:01:51,978][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:01:52,486][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:01:52,994][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:01:53,502][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:01:54,008][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:01:54,516][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:01:55,024][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:01:55,530][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:01:56,037][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:01:56,542][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:01:57,047][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:01:57,554][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:01:58,060][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:01:58,566][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:01:59,071][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:01:59,578][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:02:00,085][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:02:00,592][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:02:01,099][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:02:01,606][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:02:02,115][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:02:02,622][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:02:03,130][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:02:03,636][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:02:04,143][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:02:04,650][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:02:05,156][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:02:05,662][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:02:06,167][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:02:06,674][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:02:07,180][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:02:07,686][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:02:08,195][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:02:08,702][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:02:09,209][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:02:09,716][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:02:10,223][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:02:10,730][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:02:11,237][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:02:11,745][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:02:12,251][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:02:12,758][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:02:13,266][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:02:13,773][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:02:14,281][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:02:14,789][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:02:15,297][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:02:15,804][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:02:16,311][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:02:16,818][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:02:17,326][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:02:17,833][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:02:18,338][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:02:18,846][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:02:19,353][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:02:19,862][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:02:20,368][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:02:20,877][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:02:21,384][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:02:21,892][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:02:22,398][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:02:22,906][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:02:23,414][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:02:23,920][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:02:24,429][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:02:24,936][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:02:25,444][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:02:25,951][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:02:26,458][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:02:26,965][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:02:27,473][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:02:27,979][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:02:28,485][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:02:28,992][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:02:29,498][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:02:30,005][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:02:30,514][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:02:31,020][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:02:31,527][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:02:32,035][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:02:32,542][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:02:33,049][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:02:33,557][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:02:34,064][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:02:34,571][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:02:35,079][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:02:35,586][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 21:02:36,250][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.20%, ΔTime: 00:01:05 [2026-03-25 21:02:36,986][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:02:36,988][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:02:36,989][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:02:37,652][__main__][INFO] - Iteration 246 took 1m 14s (8.17% Gen, 90.94% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 57h 0m 11s. Estimated total time: 62h 27m 36s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 55s, 500 more iterations: 10h 24m 36s. [2026-03-25 21:02:37,654][__main__][INFO] - Starting iteration 246. [2026-03-25 21:02:38,060][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 21:02:38,060][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:02:44,549][__main__][INFO] - Number of regex retries in iteration 246: 0 [2026-03-25 21:02:44,551][__main__][INFO] - agents played in iteration 246 are Bob, Alice [2026-03-25 21:02:45,803][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:02:46,419][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:02:46,881][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:02:47,394][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:02:47,902][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:02:48,408][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:02:48,915][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:02:49,423][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:02:49,930][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:02:50,438][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:02:50,947][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:02:51,457][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:02:51,965][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:02:52,472][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:02:52,980][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:02:53,487][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:02:53,996][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:02:54,504][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:02:55,011][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:02:55,519][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:02:56,028][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:02:56,533][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:02:57,040][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:02:57,546][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:02:58,054][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:02:58,562][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:02:59,068][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:02:59,577][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:03:00,085][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:03:00,591][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:03:01,098][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:03:01,605][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:03:02,113][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:03:02,621][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:03:03,129][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:03:03,638][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:03:04,146][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:03:04,653][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:03:05,160][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:03:05,667][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:03:06,174][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:03:06,681][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:03:07,188][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:03:07,697][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:03:08,205][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:03:08,712][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:03:09,220][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:03:09,728][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:03:10,235][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:03:10,742][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:03:11,249][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:03:11,756][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:03:12,263][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:03:12,769][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:03:13,276][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:03:13,783][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:03:14,290][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:03:14,797][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:03:15,302][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:03:15,807][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:03:16,314][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:03:16,820][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:03:17,326][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:03:17,832][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:03:18,338][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:03:18,843][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:03:19,350][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:03:19,856][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:03:20,363][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:03:20,870][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:03:21,376][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:03:21,883][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:03:22,389][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:03:22,896][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:03:23,404][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:03:23,912][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:03:24,419][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:03:24,926][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:03:25,433][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:03:25,941][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:03:26,447][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:03:26,955][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:03:27,462][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:03:27,970][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:03:28,477][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:03:28,984][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:03:29,490][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:03:29,997][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:03:30,504][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:03:31,011][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:03:31,518][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:03:32,026][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:03:32,532][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:03:33,040][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:03:33,547][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:03:34,054][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:03:34,560][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:03:35,067][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:03:35,574][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:03:36,082][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:03:36,589][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:03:37,097][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:03:37,605][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:03:38,112][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:03:38,619][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:03:39,127][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:03:39,635][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:03:40,142][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:03:40,648][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:03:41,156][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:03:41,662][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:03:42,169][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:03:42,676][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:03:43,183][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:03:43,690][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:03:44,197][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:03:44,704][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:03:45,210][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:03:45,717][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:03:46,225][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:03:46,731][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:03:47,238][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:03:47,745][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:03:48,250][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:03:48,755][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:03:49,261][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:03:49,766][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:03:50,271][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:03:50,776][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:03:51,282][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 21:03:51,932][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 21:03:52,668][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:03:52,670][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:03:52,672][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:03:53,569][__main__][INFO] - Iteration 247 took 1m 15s (8.60% Gen, 90.21% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 57h 26m 50s. Estimated total time: 62h 55m 30s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 51s, 500 more iterations: 10h 29m 15s. [2026-03-25 21:03:53,571][__main__][INFO] - Starting iteration 247. [2026-03-25 21:03:53,973][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 21:03:53,974][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:04:00,833][__main__][INFO] - Number of regex retries in iteration 247: 0 [2026-03-25 21:04:00,834][__main__][INFO] - agents played in iteration 247 are Bob, Alice [2026-03-25 21:04:01,802][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:04:02,425][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:04:02,890][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:04:03,402][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:04:03,910][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:04:04,417][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:04:04,924][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:04:05,431][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:04:05,938][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:04:06,446][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:04:06,952][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:04:07,459][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:04:07,965][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:04:08,472][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:04:08,978][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:04:09,483][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:04:09,989][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:04:10,496][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:04:11,005][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:04:11,514][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:04:12,022][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:04:12,530][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:04:13,038][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:04:13,546][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:04:14,054][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:04:14,562][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:04:15,068][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:04:15,574][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:04:16,081][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:04:16,587][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:04:17,093][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:04:17,599][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:04:18,105][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:04:18,612][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:04:19,119][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:04:19,627][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:04:20,134][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:04:20,642][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:04:21,150][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:04:21,657][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:04:22,164][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:04:22,672][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:04:23,179][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:04:23,685][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:04:24,192][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:04:24,700][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:04:25,207][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:04:25,714][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:04:26,221][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:04:26,728][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:04:27,236][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:04:27,744][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:04:28,251][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:04:28,758][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:04:29,266][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:04:29,773][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:04:30,280][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:04:30,788][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:04:31,295][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:04:31,801][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:04:32,308][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:04:32,811][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:04:33,318][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:04:33,826][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:04:34,332][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:04:34,838][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:04:35,345][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:04:35,852][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:04:36,359][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:04:36,867][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:04:37,375][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:04:37,881][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:04:38,388][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:04:38,896][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:04:39,402][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:04:39,909][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:04:40,416][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:04:40,923][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:04:41,429][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:04:41,935][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:04:42,441][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:04:42,948][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:04:43,455][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:04:43,964][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:04:44,471][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:04:44,978][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:04:45,486][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:04:45,993][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:04:46,501][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:04:47,009][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:04:47,518][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:04:48,025][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:04:48,531][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:04:49,037][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:04:49,544][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:04:50,050][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:04:50,555][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:04:51,062][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:04:51,570][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:04:52,077][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:04:52,585][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:04:53,092][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:04:53,600][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:04:54,107][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:04:54,615][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:04:55,122][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:04:55,629][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:04:56,136][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:04:56,644][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:04:57,150][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:04:57,657][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:04:58,164][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:04:58,670][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:04:59,177][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:04:59,684][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:05:00,192][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:05:00,699][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:05:01,207][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:05:01,714][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:05:02,222][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:05:02,729][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:05:03,236][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:05:03,743][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:05:04,249][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:05:04,755][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:05:05,261][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:05:05,767][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:05:06,275][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:05:06,781][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:05:07,287][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21726 tokens. [2026-03-25 21:05:07,935][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 21:05:08,670][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:05:08,672][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:05:08,674][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:05:09,335][__main__][INFO] - Iteration 248 took 1m 15s (9.10% Gen, 90.02% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 18m 9s. Estimated total time: 62h 48m 6s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 36s, 500 more iterations: 10h 28m 1s. [2026-03-25 21:05:09,337][__main__][INFO] - Starting iteration 248. [2026-03-25 21:05:09,737][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 21:05:09,738][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:05:16,539][__main__][INFO] - Number of regex retries in iteration 248: 0 [2026-03-25 21:05:16,540][__main__][INFO] - agents played in iteration 248 are Bob, Alice [2026-03-25 21:05:17,517][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:05:18,135][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:05:18,599][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:05:19,110][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:05:19,618][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:05:20,125][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:05:20,633][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:05:21,140][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:05:21,647][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:05:22,154][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:05:22,663][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:05:23,171][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:05:23,678][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:05:24,186][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:05:24,692][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:05:25,201][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:05:25,708][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:05:26,216][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:05:26,723][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:05:27,231][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:05:27,737][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:05:28,245][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:05:28,752][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:05:29,260][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:05:29,765][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:05:30,273][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:05:30,779][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:05:31,287][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:05:31,793][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:05:32,301][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:05:32,806][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:05:33,312][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:05:33,817][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:05:34,326][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:05:34,835][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:05:35,345][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:05:35,852][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:05:36,361][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:05:36,867][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:05:37,377][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:05:37,884][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:05:38,394][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:05:38,904][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:05:39,415][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:05:39,924][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:05:40,431][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:05:40,940][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:05:41,449][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:05:41,957][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:05:42,465][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:05:42,973][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:05:43,480][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:05:43,986][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:05:44,496][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:05:45,004][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:05:45,510][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:05:46,018][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:05:46,525][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:05:47,031][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:05:47,538][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:05:48,044][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:05:48,549][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:05:49,056][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:05:49,561][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:05:50,067][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:05:50,573][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:05:51,080][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:05:51,588][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:05:52,096][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:05:52,604][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:05:53,111][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:05:53,620][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:05:54,127][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:05:54,636][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:05:55,142][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:05:55,651][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:05:56,157][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:05:56,665][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:05:57,173][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:05:57,680][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:05:58,187][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:05:58,695][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:05:59,203][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:05:59,709][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:06:00,218][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:06:00,725][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:06:01,234][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:06:01,741][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:06:02,249][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:06:02,756][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:06:03,264][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:06:03,773][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:06:04,281][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:06:04,787][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:06:05,297][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:06:05,804][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:06:06,312][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:06:06,819][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:06:07,328][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:06:07,835][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:06:08,344][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:06:08,851][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:06:09,359][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:06:09,866][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:06:10,373][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:06:10,879][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:06:11,387][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:06:11,896][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:06:12,404][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:06:12,914][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:06:13,422][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:06:13,931][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:06:14,439][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:06:14,948][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:06:15,455][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:06:15,962][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:06:16,469][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:06:16,978][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:06:17,485][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:06:17,992][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:06:18,499][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:06:19,006][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:06:19,513][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:06:20,019][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:06:20,525][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:06:21,031][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:06:21,537][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:06:22,044][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:06:22,550][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:06:23,055][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 21:06:23,716][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 21:06:24,459][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:06:24,461][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:06:24,463][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:06:25,122][__main__][INFO] - Iteration 249 took 1m 15s (9.02% Gen, 90.10% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 18m 5s. Estimated total time: 62h 49m 16s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 38s, 500 more iterations: 10h 28m 12s. [2026-03-25 21:06:25,124][__main__][INFO] - Starting iteration 249. [2026-03-25 21:06:25,527][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 21:06:25,528][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:06:28,227][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:06:32,134][__main__][INFO] - Number of regex retries in iteration 249: 1 [2026-03-25 21:06:32,135][__main__][INFO] - agents played in iteration 249 are Bob, Alice [2026-03-25 21:06:33,095][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:06:33,719][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:06:34,183][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:06:34,696][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:06:35,203][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:06:35,709][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:06:36,217][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:06:36,725][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:06:37,233][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:06:37,739][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:06:38,248][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:06:38,756][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:06:39,263][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:06:39,770][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:06:40,277][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:06:40,784][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:06:41,291][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:06:41,800][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:06:42,309][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:06:42,818][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:06:43,326][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:06:43,835][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:06:44,344][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:06:44,853][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:06:45,361][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:06:45,870][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:06:46,377][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:06:46,884][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:06:47,390][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:06:47,898][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:06:48,405][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:06:48,913][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:06:49,420][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:06:49,927][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:06:50,437][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:06:50,944][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:06:51,452][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:06:51,959][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:06:52,466][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:06:52,974][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:06:53,481][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:06:53,988][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:06:54,496][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:06:55,005][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:06:55,510][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:06:56,018][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:06:56,525][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:06:57,033][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:06:57,539][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:06:58,046][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:06:58,553][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:06:59,059][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:06:59,565][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:07:00,071][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:07:00,577][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:07:01,083][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:07:01,589][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:07:02,094][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:07:02,601][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:07:03,107][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:07:03,616][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:07:04,123][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:07:04,630][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:07:05,137][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:07:05,645][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:07:06,151][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:07:06,659][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:07:07,165][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:07:07,673][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:07:08,180][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:07:08,686][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:07:09,196][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:07:09,704][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:07:10,211][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:07:10,718][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:07:11,227][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:07:11,736][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:07:12,244][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:07:12,751][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:07:13,259][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:07:13,767][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:07:14,275][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:07:14,783][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:07:15,292][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:07:15,801][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:07:16,310][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:07:16,819][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:07:17,328][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:07:17,837][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:07:18,346][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:07:18,855][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:07:19,363][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:07:19,869][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:07:20,377][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:07:20,884][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:07:21,392][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:07:21,899][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:07:22,406][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:07:22,917][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:07:23,425][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:07:23,934][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:07:24,442][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:07:24,949][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:07:25,457][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:07:25,965][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:07:26,472][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:07:26,979][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:07:27,486][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:07:27,992][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:07:28,499][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:07:29,005][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:07:29,512][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:07:30,018][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:07:30,525][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:07:31,031][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:07:31,538][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:07:32,044][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:07:32,551][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:07:33,057][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:07:33,564][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:07:34,070][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:07:34,576][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:07:35,082][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:07:35,589][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:07:36,097][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:07:36,605][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:07:37,112][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:07:37,620][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:07:38,128][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:07:38,635][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 21:07:39,297][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 21:07:40,035][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:07:40,038][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:07:40,039][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:07:40,910][__main__][INFO] - Iteration 250 took 1m 15s (8.76% Gen, 90.08% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 16m 41s. Estimated total time: 62h 49m 9s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 38s, 500 more iterations: 10h 28m 11s. [2026-03-25 21:07:40,912][__main__][INFO] - Starting iteration 250. [2026-03-25 21:07:41,321][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 4 and human policies 1. [2026-03-25 21:07:41,322][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:07:48,321][__main__][INFO] - Number of regex retries in iteration 250: 0 [2026-03-25 21:07:48,322][__main__][INFO] - agents played in iteration 250 are Bob, Alice [2026-03-25 21:07:49,282][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:07:49,905][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:07:50,368][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:07:50,879][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:07:51,385][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:07:51,894][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:07:52,400][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:07:52,907][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:07:53,414][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:07:53,921][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:07:54,427][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:07:54,935][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:07:55,441][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:07:55,947][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:07:56,454][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:07:56,961][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:07:57,469][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:07:57,976][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:07:58,486][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:07:58,994][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:07:59,501][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:08:00,010][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:08:00,519][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:08:01,027][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:08:01,535][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:08:02,043][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:08:02,551][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:08:03,057][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:08:03,563][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:08:04,071][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:08:04,579][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:08:05,085][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:08:05,593][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:08:06,100][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:08:06,609][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:08:07,117][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:08:07,625][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:08:08,134][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:08:08,643][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:08:09,150][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:08:09,658][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:08:10,166][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:08:10,673][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:08:11,180][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:08:11,686][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:08:12,197][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:08:12,705][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:08:13,212][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:08:13,719][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:08:14,227][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:08:14,740][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:08:15,249][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:08:15,758][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:08:16,267][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:08:16,776][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:08:17,284][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:08:17,796][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:08:18,306][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:08:18,814][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:08:19,323][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:08:19,832][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:08:20,340][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:08:20,849][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:08:21,358][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:08:21,867][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:08:22,375][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:08:22,881][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:08:23,387][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:08:23,895][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:08:24,402][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:08:24,909][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:08:25,416][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:08:25,923][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:08:26,430][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:08:26,936][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:08:27,444][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:08:27,951][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:08:28,458][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:08:28,965][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:08:29,471][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:08:29,978][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:08:30,485][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:08:30,992][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:08:31,500][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:08:32,008][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:08:32,517][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:08:33,026][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:08:33,533][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:08:34,041][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:08:34,549][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:08:35,056][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:08:35,562][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:08:36,069][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:08:36,576][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:08:37,083][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:08:37,589][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:08:38,098][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:08:38,606][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:08:39,114][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:08:39,622][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:08:40,130][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:08:40,638][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:08:41,145][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:08:41,652][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:08:42,160][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:08:42,668][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:08:43,176][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:08:43,682][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:08:44,190][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:08:44,698][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:08:45,205][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:08:45,715][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:08:46,223][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:08:46,730][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:08:47,239][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:08:47,747][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:08:48,258][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:08:48,767][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:08:49,275][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:08:49,785][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:08:50,295][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:08:50,803][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:08:51,312][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:08:51,821][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:08:52,330][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:08:52,839][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:08:53,347][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:08:53,856][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:08:54,365][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:08:54,873][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 21:08:55,538][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 21:08:56,286][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:08:56,288][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:08:56,290][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:08:59,870][__main__][INFO] - Iteration 251 took 1m 18s (8.91% Gen, 86.53% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 59h 53m 41s. Estimated total time: 65h 27m 28s. Time estimates for 10 more iterations: 13m 5s, 100 more iterations: 2h 10m 54s, 500 more iterations: 10h 54m 34s. [2026-03-25 21:08:59,872][__main__][INFO] - Starting iteration 251. [2026-03-25 21:09:00,277][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:09:00,278][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:09:02,559][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:09:06,951][__main__][INFO] - Number of regex retries in iteration 251: 1 [2026-03-25 21:09:06,951][__main__][INFO] - agents played in iteration 251 are Bob, Alice [2026-03-25 21:09:07,931][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:09:08,562][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:09:09,025][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:09:09,538][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:09:10,045][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:09:10,552][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:09:11,059][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:09:11,567][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:09:12,074][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:09:12,581][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:09:13,087][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:09:13,595][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:09:14,102][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:09:14,608][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:09:15,116][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:09:15,624][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:09:16,131][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:09:16,638][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:09:17,145][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:09:17,652][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:09:18,159][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:09:18,666][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:09:19,172][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:09:19,679][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:09:20,186][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:09:20,693][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:09:21,203][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:09:21,711][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:09:22,219][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:09:22,727][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:09:23,234][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:09:23,742][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:09:24,250][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:09:24,758][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:09:25,264][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:09:25,770][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:09:26,277][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:09:26,783][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:09:27,289][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:09:27,797][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:09:28,305][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:09:28,811][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:09:29,320][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:09:29,827][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:09:30,334][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:09:30,842][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:09:31,349][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:09:31,856][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:09:32,363][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:09:32,870][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:09:33,379][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:09:33,887][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:09:34,396][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:09:34,905][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:09:35,414][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:09:35,922][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:09:36,432][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:09:36,940][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:09:37,447][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:09:37,955][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:09:38,463][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:09:38,971][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:09:39,479][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:09:39,986][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:09:40,493][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:09:41,000][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:09:41,507][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:09:42,015][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:09:42,523][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:09:43,031][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:09:43,537][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:09:44,045][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:09:44,551][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:09:45,058][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:09:45,564][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:09:46,071][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:09:46,577][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:09:47,083][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:09:47,590][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:09:48,099][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:09:48,606][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:09:49,113][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:09:49,621][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:09:50,128][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:09:50,635][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:09:51,142][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:09:51,648][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:09:52,157][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:09:52,665][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:09:53,172][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:09:53,679][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:09:54,186][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:09:54,694][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:09:55,201][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:09:55,708][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:09:56,218][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:09:56,726][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:09:57,232][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:09:57,735][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:09:58,241][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:09:58,747][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:09:59,254][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:09:59,761][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:10:00,268][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:10:00,775][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:10:01,282][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:10:01,788][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:10:02,296][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:10:02,803][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:10:03,310][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:10:03,817][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:10:04,324][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:10:04,831][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:10:05,338][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:10:05,845][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:10:06,353][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:10:06,861][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:10:07,369][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:10:07,878][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:10:08,385][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:10:08,894][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:10:09,402][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:10:09,910][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:10:10,417][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:10:10,925][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:10:11,434][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:10:11,941][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:10:12,448][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:10:12,957][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:10:13,465][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 21:10:14,125][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 21:10:14,862][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:10:14,864][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:10:14,866][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:10:15,579][__main__][INFO] - Iteration 252 took 1m 15s (8.86% Gen, 90.19% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 10m 6s. Estimated total time: 62h 45m 8s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 30s, 500 more iterations: 10h 27m 31s. [2026-03-25 21:10:15,581][__main__][INFO] - Starting iteration 252. [2026-03-25 21:10:15,984][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:10:15,984][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:10:16,601][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:10:20,997][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:10:23,185][__main__][INFO] - Number of regex retries in iteration 252: 2 [2026-03-25 21:10:23,186][__main__][INFO] - agents played in iteration 252 are Bob, Alice [2026-03-25 21:10:24,174][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:10:24,805][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:10:25,270][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:10:25,784][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:10:26,292][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:10:26,800][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:10:27,308][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:10:27,817][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:10:28,325][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:10:28,834][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:10:29,342][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:10:29,849][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:10:30,356][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:10:30,863][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:10:31,370][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:10:31,876][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:10:32,383][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:10:32,890][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:10:33,398][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:10:33,905][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:10:34,412][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:10:34,918][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:10:35,426][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:10:35,933][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:10:36,440][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:10:36,947][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:10:37,455][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:10:37,962][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:10:38,470][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:10:38,977][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:10:39,484][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:10:39,991][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:10:40,499][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:10:41,006][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:10:41,515][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:10:42,023][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:10:42,530][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:10:43,038][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:10:43,545][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:10:44,053][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:10:44,559][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:10:45,067][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:10:45,574][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:10:46,082][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:10:46,589][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:10:47,097][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:10:47,604][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:10:48,112][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:10:48,618][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:10:49,127][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:10:49,635][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:10:50,141][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:10:50,647][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:10:51,154][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:10:51,661][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:10:52,167][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:10:52,673][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:10:53,179][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:10:53,685][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:10:54,193][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:10:54,699][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:10:55,205][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:10:55,714][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:10:56,220][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:10:56,727][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:10:57,234][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:10:57,742][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:10:58,249][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:10:58,758][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:10:59,266][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:10:59,777][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:11:00,285][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:11:00,793][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:11:01,301][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:11:01,808][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:11:02,316][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:11:02,822][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:11:03,329][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:11:03,837][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:11:04,343][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:11:04,850][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:11:05,357][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:11:05,864][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:11:06,370][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:11:06,878][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:11:07,385][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:11:07,890][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:11:08,398][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:11:08,905][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:11:09,412][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:11:09,919][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:11:10,425][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:11:10,933][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:11:11,440][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:11:11,946][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:11:12,455][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:11:12,961][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:11:13,468][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:11:13,975][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:11:14,481][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:11:14,990][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:11:15,497][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:11:16,004][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:11:16,509][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:11:17,017][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:11:17,521][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:11:18,028][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:11:18,536][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:11:19,045][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:11:19,553][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:11:20,060][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:11:20,566][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:11:21,074][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:11:21,581][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:11:22,087][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:11:22,594][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:11:23,100][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:11:23,606][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:11:24,113][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:11:24,619][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:11:25,125][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:11:25,632][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:11:26,138][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:11:26,646][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:11:27,153][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:11:27,659][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:11:28,165][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:11:28,671][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:11:29,179][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:11:29,687][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21715 tokens. [2026-03-25 21:11:30,352][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-25 21:11:31,098][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:11:31,100][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:11:31,102][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:11:31,824][__main__][INFO] - Iteration 253 took 1m 15s (9.50% Gen, 89.55% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 57h 35m 42s. Estimated total time: 63h 12m 1s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 24s, 500 more iterations: 10h 32m 0s. [2026-03-25 21:11:31,826][__main__][INFO] - Starting iteration 253. [2026-03-25 21:11:32,227][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:11:32,228][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:11:39,029][__main__][INFO] - Number of regex retries in iteration 253: 0 [2026-03-25 21:11:39,030][__main__][INFO] - agents played in iteration 253 are Bob, Alice [2026-03-25 21:11:39,989][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:11:40,619][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:11:41,337][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:11:41,849][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:11:42,357][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:11:42,866][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:11:43,373][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:11:43,881][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:11:44,389][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:11:44,897][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:11:45,405][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:11:45,912][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:11:46,419][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:11:46,926][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:11:47,433][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:11:47,942][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:11:48,449][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:11:48,955][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:11:49,461][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:11:49,967][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:11:50,473][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:11:50,979][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:11:51,485][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:11:51,990][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:11:52,496][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:11:53,003][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:11:53,509][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:11:54,016][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:11:54,523][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:11:55,029][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:11:55,535][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:11:56,041][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:11:56,547][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:11:57,054][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:11:57,561][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:11:58,067][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:11:58,576][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:11:59,083][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:11:59,589][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:12:00,097][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:12:00,605][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:12:01,111][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:12:01,619][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:12:02,126][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:12:02,634][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:12:03,141][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:12:03,648][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:12:04,155][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:12:04,662][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:12:05,168][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:12:05,677][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:12:06,185][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:12:06,698][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:12:07,208][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:12:07,717][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:12:08,226][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:12:08,736][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:12:09,245][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:12:09,752][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:12:10,259][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:12:10,766][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:12:11,273][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:12:11,780][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:12:12,285][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:12:12,792][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:12:13,300][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:12:13,808][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:12:14,317][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:12:14,826][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:12:15,335][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:12:15,845][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:12:16,354][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:12:16,864][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:12:17,372][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:12:17,879][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:12:18,386][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:12:18,895][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:12:19,401][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:12:19,907][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:12:20,416][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:12:20,923][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:12:21,431][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:12:21,938][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:12:22,441][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:12:22,949][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:12:23,456][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:12:23,963][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:12:24,470][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:12:24,977][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:12:25,484][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:12:25,990][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:12:26,497][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:12:27,003][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:12:27,510][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:12:28,016][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:12:28,523][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:12:29,030][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:12:29,537][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:12:30,044][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:12:30,550][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:12:31,058][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:12:31,565][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:12:32,071][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:12:32,576][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:12:33,082][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:12:33,589][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:12:34,095][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:12:34,601][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:12:35,105][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:12:35,613][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:12:36,119][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:12:36,625][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:12:37,130][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:12:37,637][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:12:38,146][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:12:38,655][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:12:39,164][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:12:39,673][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:12:40,181][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:12:40,689][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:12:41,198][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:12:41,707][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:12:42,216][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:12:42,722][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:12:43,229][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:12:43,737][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:12:44,245][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:12:44,751][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:12:45,258][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:12:45,765][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21727 tokens. [2026-03-25 21:12:46,481][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-25 21:12:47,230][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:12:47,232][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:12:47,234][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:12:48,106][__main__][INFO] - Iteration 254 took 1m 15s (8.96% Gen, 89.88% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 57h 36m 22s. Estimated total time: 63h 13m 57s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 27s, 500 more iterations: 10h 32m 19s. [2026-03-25 21:12:48,108][__main__][INFO] - Starting iteration 254. [2026-03-25 21:12:48,509][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:12:48,509][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:12:55,132][__main__][INFO] - Number of regex retries in iteration 254: 0 [2026-03-25 21:12:55,133][__main__][INFO] - agents played in iteration 254 are Bob, Alice [2026-03-25 21:12:56,102][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:12:56,735][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:12:57,199][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:12:57,710][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:12:58,217][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:12:58,724][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:12:59,231][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:12:59,736][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:13:00,242][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:13:00,747][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:13:01,259][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:13:01,767][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:13:02,277][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:13:02,784][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:13:03,292][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:13:03,801][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:13:04,310][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:13:04,820][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:13:05,327][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:13:05,833][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:13:06,340][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:13:06,848][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:13:07,355][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:13:07,862][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:13:08,367][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:13:08,875][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:13:09,382][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:13:09,889][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:13:10,398][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:13:10,906][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:13:11,414][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:13:11,921][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:13:12,429][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:13:12,937][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:13:13,446][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:13:13,956][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:13:14,464][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:13:14,973][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:13:15,481][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:13:15,989][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:13:16,498][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:13:17,006][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:13:17,514][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:13:18,022][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:13:18,528][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:13:19,036][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:13:19,543][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:13:20,050][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:13:20,557][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:13:21,064][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:13:21,571][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:13:22,078][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:13:22,584][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:13:23,091][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:13:23,599][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:13:24,105][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:13:24,613][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:13:25,120][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:13:25,627][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:13:26,135][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:13:26,642][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:13:27,150][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:13:27,656][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:13:28,163][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:13:28,670][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:13:29,177][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:13:29,685][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:13:30,191][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:13:30,698][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:13:31,205][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:13:31,712][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:13:32,219][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:13:32,727][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:13:33,235][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:13:33,744][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:13:34,252][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:13:34,760][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:13:35,269][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:13:35,779][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:13:36,286][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:13:36,796][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:13:37,304][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:13:37,811][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:13:38,317][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:13:38,825][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:13:39,332][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:13:39,839][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:13:40,346][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:13:40,854][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:13:41,361][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:13:41,868][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:13:42,376][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:13:42,884][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:13:43,392][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:13:43,899][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:13:44,405][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:13:44,913][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:13:45,421][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:13:45,929][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:13:46,438][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:13:46,946][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:13:47,455][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:13:47,963][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:13:48,470][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:13:48,978][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:13:49,486][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:13:49,994][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:13:50,501][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:13:51,009][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:13:51,516][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:13:52,023][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:13:52,530][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:13:53,038][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:13:53,545][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:13:54,052][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:13:54,559][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:13:55,066][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:13:55,573][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:13:56,079][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:13:56,585][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:13:57,092][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:13:57,599][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:13:58,106][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:13:58,614][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:13:59,122][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:13:59,630][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:14:00,136][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:14:00,643][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:14:01,150][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:14:01,658][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21746 tokens. [2026-03-25 21:14:02,319][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 21:14:03,074][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:14:03,076][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:14:03,078][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:14:03,863][__main__][INFO] - Iteration 255 took 1m 15s (8.79% Gen, 90.17% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 8m 55s. Estimated total time: 62h 47m 45s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 35s, 500 more iterations: 10h 27m 57s. [2026-03-25 21:14:03,865][__main__][INFO] - Starting iteration 255. [2026-03-25 21:14:04,268][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:14:04,268][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:14:10,762][__main__][INFO] - Number of regex retries in iteration 255: 0 [2026-03-25 21:14:10,763][__main__][INFO] - agents played in iteration 255 are Bob, Alice [2026-03-25 21:14:11,728][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:14:12,347][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:14:12,810][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:14:13,321][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:14:13,828][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:14:14,334][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:14:14,840][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:14:15,346][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:14:15,852][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:14:16,358][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:14:16,868][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:14:17,374][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:14:17,882][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:14:18,390][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:14:18,896][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:14:19,403][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:14:19,911][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:14:20,418][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:14:20,927][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:14:21,436][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:14:21,943][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:14:22,451][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:14:22,958][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:14:23,465][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:14:23,972][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:14:24,480][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:14:24,987][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:14:25,496][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:14:26,004][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:14:26,512][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:14:27,020][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:14:27,526][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:14:28,036][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:14:28,544][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:14:29,050][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:14:29,557][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:14:30,063][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:14:30,570][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:14:31,076][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:14:31,581][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:14:32,085][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:14:32,592][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:14:33,098][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:14:33,605][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:14:34,112][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:14:34,619][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:14:35,125][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:14:35,631][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:14:36,136][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:14:36,642][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:14:37,151][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:14:37,676][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:14:38,188][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:14:38,697][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:14:39,204][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:14:39,715][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:14:40,222][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:14:40,731][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:14:41,237][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:14:41,743][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:14:42,248][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:14:42,753][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:14:43,258][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:14:43,763][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:14:44,268][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:14:44,774][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:14:45,279][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:14:45,785][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:14:46,290][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:14:46,796][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:14:47,302][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:14:47,808][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:14:48,317][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:14:48,823][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:14:49,330][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:14:49,837][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:14:50,344][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:14:50,850][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:14:51,357][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:14:51,864][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:14:52,370][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:14:52,878][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:14:53,386][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:14:53,893][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:14:54,401][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:14:54,909][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:14:55,418][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:14:55,926][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:14:56,434][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:14:56,942][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:14:57,450][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:14:57,958][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:14:58,466][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:14:58,975][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:14:59,483][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:14:59,990][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:15:00,497][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:15:01,006][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:15:01,513][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:15:02,020][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:15:02,527][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:15:03,034][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:15:03,541][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:15:04,047][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:15:04,553][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:15:05,060][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:15:05,567][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:15:06,073][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:15:06,578][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:15:07,085][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:15:07,591][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:15:08,097][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:15:08,603][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:15:09,109][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:15:09,619][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:15:10,128][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:15:10,636][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:15:11,145][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:15:11,654][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:15:12,162][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:15:12,669][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:15:13,178][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:15:13,685][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:15:14,192][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:15:14,699][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:15:15,205][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:15:15,712][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:15:16,218][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:15:16,724][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:15:17,232][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 21:15:17,889][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.38%, ΔTime: 00:01:05 [2026-03-25 21:15:18,639][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:15:18,641][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:15:18,643][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:15:19,352][__main__][INFO] - Iteration 256 took 1m 15s (8.65% Gen, 90.40% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 54m 9s. Estimated total time: 62h 34m 15s. Time estimates for 10 more iterations: 12m 30s, 100 more iterations: 2h 5m 8s, 500 more iterations: 10h 25m 42s. [2026-03-25 21:15:19,354][__main__][INFO] - Starting iteration 256. [2026-03-25 21:15:19,754][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:15:19,755][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:15:20,395][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:15:21,621][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:15:22,674][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:15:26,765][__main__][INFO] - Number of regex retries in iteration 256: 3 [2026-03-25 21:15:26,766][__main__][INFO] - agents played in iteration 256 are Bob, Alice [2026-03-25 21:15:27,736][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:15:28,373][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:15:28,838][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:15:29,351][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:15:29,860][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:15:30,367][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:15:30,875][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:15:31,383][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:15:31,891][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:15:32,399][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:15:32,909][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:15:33,418][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:15:33,927][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:15:34,435][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:15:34,944][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:15:35,453][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:15:35,961][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:15:36,469][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:15:36,978][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:15:37,486][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:15:37,994][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:15:38,502][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:15:39,009][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:15:39,517][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:15:40,026][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:15:40,534][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:15:41,042][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:15:41,549][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:15:42,054][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:15:42,562][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:15:43,068][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:15:43,575][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:15:44,082][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:15:44,589][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:15:45,099][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:15:45,608][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:15:46,116][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:15:46,625][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:15:47,134][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:15:47,643][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:15:48,151][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:15:48,659][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:15:49,166][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:15:49,674][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:15:50,181][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:15:50,687][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:15:51,196][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:15:51,703][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:15:52,210][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:15:52,718][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:15:53,225][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:15:53,732][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:15:54,239][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:15:54,746][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:15:55,255][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:15:55,762][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:15:56,270][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:15:56,777][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:15:57,285][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:15:57,793][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:15:58,300][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:15:58,808][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:15:59,316][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:15:59,824][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:16:00,331][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:16:00,838][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:16:01,346][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:16:01,854][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:16:02,361][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:16:02,869][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:16:03,377][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:16:03,885][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:16:04,393][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:16:04,900][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:16:05,408][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:16:05,917][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:16:06,426][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:16:06,935][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:16:07,444][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:16:07,952][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:16:08,461][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:16:08,969][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:16:09,477][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:16:09,985][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:16:10,493][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:16:11,002][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:16:11,511][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:16:12,020][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:16:12,528][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:16:13,038][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:16:13,545][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:16:14,052][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:16:14,558][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:16:15,065][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:16:15,572][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:16:16,078][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:16:16,585][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:16:17,092][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:16:17,600][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:16:18,109][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:16:18,619][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:16:19,128][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:16:19,637][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:16:20,146][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:16:20,655][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:16:21,163][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:16:21,670][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:16:22,176][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:16:22,683][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:16:23,191][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:16:23,697][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:16:24,204][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:16:24,712][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:16:25,219][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:16:25,728][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:16:26,234][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:16:26,742][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:16:27,250][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:16:27,758][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:16:28,264][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:16:28,772][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:16:29,280][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:16:29,787][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:16:30,296][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:16:30,804][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:16:31,311][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:16:31,819][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:16:32,327][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:16:32,836][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:16:33,345][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 21:16:34,007][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 21:16:34,762][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:16:34,764][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:16:34,765][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:16:35,610][__main__][INFO] - Iteration 257 took 1m 15s (9.24% Gen, 89.64% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 57h 31m 25s. Estimated total time: 63h 12m 48s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 25s, 500 more iterations: 10h 32m 8s. [2026-03-25 21:16:35,612][__main__][INFO] - Starting iteration 257. [2026-03-25 21:16:36,014][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:16:36,014][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:16:39,659][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:16:43,364][__main__][INFO] - Number of regex retries in iteration 257: 1 [2026-03-25 21:16:43,365][__main__][INFO] - agents played in iteration 257 are Bob, Alice [2026-03-25 21:16:44,388][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:16:45,024][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:16:45,488][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:16:46,000][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:16:46,507][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:16:47,013][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:16:47,521][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:16:48,028][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:16:48,536][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:16:49,043][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:16:49,552][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:16:50,060][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:16:50,568][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:16:51,075][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:16:51,582][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:16:52,088][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:16:52,595][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:16:53,102][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:16:53,611][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:16:54,121][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:16:54,629][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:16:55,137][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:16:55,646][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:16:56,155][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:16:56,663][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:16:57,171][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:16:57,678][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:16:58,184][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:16:58,691][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:16:59,198][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:16:59,704][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:17:00,210][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:17:00,718][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:17:01,226][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:17:01,734][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:17:02,243][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:17:02,752][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:17:03,260][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:17:03,767][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:17:04,276][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:17:04,784][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:17:05,292][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:17:05,799][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:17:06,305][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:17:06,812][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:17:07,320][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:17:07,827][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:17:08,334][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:17:08,841][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:17:09,348][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:17:09,856][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:17:10,365][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:17:10,873][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:17:11,381][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:17:11,888][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:17:12,397][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:17:12,905][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:17:13,413][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:17:13,921][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:17:14,429][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:17:14,936][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:17:15,443][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:17:15,950][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:17:16,458][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:17:16,965][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:17:17,473][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:17:17,979][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:17:18,487][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:17:18,994][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:17:19,502][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:17:20,008][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:17:20,517][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:17:21,024][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:17:21,530][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:17:22,038][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:17:22,545][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:17:23,054][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:17:23,561][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:17:24,068][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:17:24,577][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:17:25,084][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:17:25,591][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:17:26,098][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:17:26,606][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:17:27,114][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:17:27,622][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:17:28,130][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:17:28,638][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:17:29,146][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:17:29,654][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:17:30,161][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:17:30,668][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:17:31,175][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:17:31,683][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:17:32,189][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:17:32,697][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:17:33,204][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:17:33,711][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:17:34,219][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:17:34,728][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:17:35,235][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:17:35,743][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:17:36,250][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:17:36,757][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:17:37,266][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:17:37,772][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:17:38,279][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:17:38,786][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:17:39,293][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:17:39,801][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:17:40,307][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:17:40,815][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:17:41,323][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:17:41,830][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:17:42,338][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:17:42,846][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:17:43,354][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:17:43,861][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:17:44,370][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:17:44,877][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:17:45,386][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:17:45,894][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:17:46,401][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:17:46,909][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:17:47,417][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:17:47,924][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:17:48,433][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:17:48,940][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:17:49,448][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:17:49,957][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 21:17:50,625][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-25 21:17:51,378][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:17:51,380][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:17:51,381][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:17:52,046][__main__][INFO] - Iteration 258 took 1m 16s (9.67% Gen, 89.46% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 57h 39m 1s. Estimated total time: 63h 21m 39s. Time estimates for 10 more iterations: 12m 40s, 100 more iterations: 2h 6m 43s, 500 more iterations: 10h 33m 36s. [2026-03-25 21:17:52,048][__main__][INFO] - Starting iteration 258. [2026-03-25 21:17:52,452][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:17:52,452][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:17:53,065][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:17:56,459][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:17:59,366][__main__][INFO] - Number of regex retries in iteration 258: 2 [2026-03-25 21:17:59,367][__main__][INFO] - agents played in iteration 258 are Bob, Alice [2026-03-25 21:18:00,327][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:18:00,962][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:18:01,426][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:18:01,938][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:18:02,445][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:18:02,952][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:18:03,459][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:18:03,965][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:18:04,473][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:18:04,980][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:18:05,490][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:18:05,998][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:18:06,505][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:18:07,015][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:18:07,522][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:18:08,030][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:18:08,538][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:18:09,047][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:18:09,555][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:18:10,062][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:18:10,569][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:18:11,077][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:18:11,585][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:18:12,092][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:18:12,600][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:18:13,108][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:18:13,617][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:18:14,124][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:18:14,631][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:18:15,139][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:18:15,647][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:18:16,153][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:18:16,661][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:18:17,168][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:18:17,679][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:18:18,188][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:18:18,697][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:18:19,206][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:18:19,715][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:18:20,224][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:18:20,733][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:18:21,241][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:18:21,748][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:18:22,256][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:18:22,764][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:18:23,271][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:18:23,780][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:18:24,287][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:18:24,794][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:18:25,302][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:18:25,809][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:18:26,318][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:18:26,827][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:18:27,335][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:18:27,843][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:18:28,352][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:18:28,860][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:18:29,368][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:18:29,876][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:18:30,383][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:18:30,889][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:18:31,398][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:18:31,906][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:18:32,415][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:18:32,922][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:18:33,430][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:18:33,939][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:18:34,446][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:18:34,953][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:18:35,460][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:18:35,967][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:18:36,474][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:18:36,980][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:18:37,486][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:18:37,994][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:18:38,501][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:18:39,008][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:18:39,516][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:18:40,023][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:18:40,530][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:18:41,037][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:18:41,544][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:18:42,050][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:18:42,557][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:18:43,063][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:18:43,572][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:18:44,079][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:18:44,586][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:18:45,093][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:18:45,601][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:18:46,107][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:18:46,614][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:18:47,121][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:18:47,628][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:18:48,135][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:18:48,642][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:18:49,150][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:18:49,656][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:18:50,164][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:18:50,672][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:18:51,180][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:18:51,688][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:18:52,197][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:18:52,705][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:18:53,213][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:18:53,721][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:18:54,228][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:18:54,736][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:18:55,243][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:18:55,748][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:18:56,254][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:18:56,761][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:18:57,269][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:18:57,776][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:18:58,285][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:18:58,794][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:18:59,303][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:18:59,811][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:19:00,319][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:19:00,827][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:19:01,336][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:19:01,845][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:19:02,352][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:19:02,859][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:19:03,366][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:19:03,875][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:19:04,382][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:19:04,889][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:19:05,396][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:19:05,904][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 21:19:06,577][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 21:19:07,336][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:19:07,338][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:19:07,340][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:19:08,054][__main__][INFO] - Iteration 259 took 1m 15s (9.15% Gen, 89.91% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 16m 14s. Estimated total time: 63h 0m 8s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 0s, 500 more iterations: 10h 30m 1s. [2026-03-25 21:19:08,056][__main__][INFO] - Starting iteration 259. [2026-03-25 21:19:08,459][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:19:08,460][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:19:10,135][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:19:11,253][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:19:15,259][__main__][INFO] - Number of regex retries in iteration 259: 2 [2026-03-25 21:19:15,260][__main__][INFO] - agents played in iteration 259 are Bob, Alice [2026-03-25 21:19:16,228][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:19:16,859][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:19:17,323][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:19:17,836][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:19:18,344][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:19:18,851][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:19:19,358][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:19:19,865][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:19:20,372][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:19:20,880][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:19:21,388][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:19:21,897][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:19:22,405][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:19:22,911][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:19:23,418][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:19:23,925][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:19:24,433][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:19:24,940][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:19:25,448][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:19:25,956][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:19:26,463][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:19:26,973][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:19:27,480][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:19:27,987][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:19:28,495][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:19:29,003][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:19:29,510][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:19:30,018][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:19:30,527][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:19:31,035][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:19:31,543][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:19:32,050][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:19:32,558][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:19:33,066][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:19:33,575][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:19:34,082][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:19:34,589][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:19:35,098][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:19:35,605][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:19:36,113][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:19:36,621][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:19:37,128][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:19:37,637][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:19:38,145][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:19:38,652][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:19:39,160][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:19:39,666][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:19:40,173][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:19:40,680][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:19:41,187][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:19:41,693][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:19:42,199][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:19:42,706][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:19:43,211][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:19:43,717][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:19:44,224][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:19:44,731][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:19:45,238][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:19:45,749][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:19:46,273][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:19:46,781][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:19:47,289][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:19:47,798][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:19:48,307][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:19:48,815][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:19:49,324][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:19:49,831][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:19:50,339][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:19:50,847][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:19:51,355][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:19:51,863][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:19:52,370][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:19:52,877][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:19:53,384][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:19:53,893][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:19:54,401][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:19:54,908][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:19:55,419][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:19:55,929][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:19:56,437][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:19:56,945][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:19:57,452][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:19:57,960][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:19:58,468][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:19:58,977][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:19:59,485][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:19:59,992][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:20:00,501][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:20:01,008][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:20:01,518][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:20:02,027][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:20:02,535][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:20:03,043][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:20:03,552][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:20:04,060][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:20:04,568][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:20:05,077][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:20:05,585][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:20:06,092][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:20:06,599][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:20:07,106][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:20:07,615][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:20:08,122][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:20:08,629][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:20:09,138][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:20:09,646][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:20:10,153][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:20:10,661][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:20:11,168][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:20:11,676][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:20:12,183][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:20:12,690][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:20:13,199][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:20:13,707][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:20:14,213][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:20:14,720][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:20:15,227][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:20:15,734][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:20:16,240][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:20:16,747][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:20:17,253][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:20:17,760][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:20:18,268][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:20:18,776][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:20:19,286][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:20:19,795][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:20:20,303][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:20:20,811][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:20:21,321][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:20:21,830][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21734 tokens. [2026-03-25 21:20:22,498][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:05 [2026-03-25 21:20:23,250][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:20:23,253][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:20:23,254][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:20:24,048][__main__][INFO] - Iteration 260 took 1m 15s (9.00% Gen, 89.95% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 57h 14m 17s. Estimated total time: 62h 59m 28s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 58s, 500 more iterations: 10h 29m 54s. [2026-03-25 21:20:24,050][__main__][INFO] - Starting iteration 260. [2026-03-25 21:20:24,451][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:20:24,451][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:20:30,834][__main__][INFO] - Number of regex retries in iteration 260: 0 [2026-03-25 21:20:30,834][__main__][INFO] - agents played in iteration 260 are Bob, Alice [2026-03-25 21:20:31,808][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:20:32,433][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:20:32,898][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:20:33,412][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:20:33,920][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:20:34,429][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:20:34,937][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:20:35,445][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:20:35,954][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:20:36,463][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:20:36,972][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:20:37,481][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:20:37,987][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:20:38,494][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:20:39,001][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:20:39,509][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:20:40,018][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:20:40,527][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:20:41,035][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:20:41,544][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:20:42,053][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:20:42,561][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:20:43,069][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:20:43,580][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:20:44,089][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:20:44,600][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:20:45,108][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:20:45,617][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:20:46,125][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:20:46,633][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:20:47,140][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:20:47,648][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:20:48,157][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:20:48,664][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:20:49,172][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:20:49,680][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:20:50,188][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:20:50,697][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:20:51,205][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:20:51,713][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:20:52,221][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:20:52,730][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:20:53,237][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:20:53,745][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:20:54,252][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:20:54,758][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:20:55,265][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:20:55,772][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:20:56,279][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:20:56,786][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:20:57,289][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:20:57,796][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:20:58,300][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:20:58,804][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:20:59,307][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:20:59,811][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:21:00,316][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:21:00,822][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:21:01,329][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:21:01,837][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:21:02,343][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:21:02,851][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:21:03,358][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:21:03,865][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:21:04,373][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:21:04,880][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:21:05,389][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:21:05,898][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:21:06,407][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:21:06,916][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:21:07,425][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:21:07,935][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:21:08,444][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:21:08,953][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:21:09,461][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:21:09,969][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:21:10,478][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:21:10,987][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:21:11,495][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:21:12,004][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:21:12,512][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:21:13,021][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:21:13,529][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:21:14,038][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:21:14,546][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:21:15,054][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:21:15,562][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:21:16,070][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:21:16,577][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:21:17,085][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:21:17,593][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:21:18,101][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:21:18,609][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:21:19,118][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:21:19,627][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:21:20,137][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:21:20,644][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:21:21,151][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:21:21,661][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:21:22,169][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:21:22,677][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:21:23,185][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:21:23,692][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:21:24,199][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:21:24,706][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:21:25,215][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:21:25,722][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:21:26,228][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:21:26,735][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:21:27,241][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:21:27,748][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:21:28,255][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:21:28,761][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:21:29,269][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:21:29,773][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:21:30,277][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:21:30,779][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:21:31,283][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:21:31,786][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:21:32,290][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:21:32,794][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:21:33,298][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:21:33,804][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:21:34,310][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:21:34,819][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:21:35,327][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:21:35,833][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:21:36,341][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:21:36,847][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:21:37,355][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 21:21:38,007][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:05 [2026-03-25 21:21:38,757][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:21:38,759][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:21:38,761][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:21:39,453][__main__][INFO] - Iteration 261 took 1m 15s (8.51% Gen, 90.57% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 43m 41s. Estimated total time: 62h 30m 7s. Time estimates for 10 more iterations: 12m 30s, 100 more iterations: 2h 5m 0s, 500 more iterations: 10h 25m 1s. [2026-03-25 21:21:39,455][__main__][INFO] - Starting iteration 261. [2026-03-25 21:21:39,857][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:21:39,857][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:21:40,460][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:21:47,007][__main__][INFO] - Number of regex retries in iteration 261: 1 [2026-03-25 21:21:47,008][__main__][INFO] - agents played in iteration 261 are Bob, Alice [2026-03-25 21:21:47,983][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:21:48,614][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:21:49,077][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:21:49,589][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:21:50,096][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:21:50,603][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:21:51,109][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:21:51,619][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:21:52,128][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:21:52,635][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:21:53,142][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:21:53,648][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:21:54,154][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:21:54,660][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:21:55,166][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:21:55,673][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:21:56,179][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:21:56,685][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:21:57,193][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:21:57,699][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:21:58,206][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:21:58,713][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:21:59,220][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:21:59,727][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:22:00,234][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:22:00,741][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:22:01,250][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:22:01,757][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:22:02,265][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:22:02,772][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:22:03,278][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:22:03,785][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:22:04,291][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:22:04,798][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:22:05,306][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:22:05,813][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:22:06,321][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:22:06,829][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:22:07,337][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:22:07,845][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:22:08,353][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:22:08,861][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:22:09,368][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:22:09,874][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:22:10,382][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:22:10,889][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:22:11,396][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:22:11,903][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:22:12,410][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:22:12,917][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:22:13,424][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:22:13,930][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:22:14,439][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:22:14,946][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:22:15,452][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:22:15,960][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:22:16,466][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:22:16,973][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:22:17,480][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:22:17,987][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:22:18,496][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:22:19,004][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:22:19,511][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:22:20,019][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:22:20,527][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:22:21,035][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:22:21,542][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:22:22,049][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:22:22,555][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:22:23,063][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:22:23,570][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:22:24,076][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:22:24,582][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:22:25,088][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:22:25,593][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:22:26,100][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:22:26,605][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:22:27,111][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:22:27,617][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:22:28,123][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:22:28,629][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:22:29,135][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:22:29,642][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:22:30,148][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:22:30,655][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:22:31,162][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:22:31,668][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:22:32,176][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:22:32,682][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:22:33,188][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:22:33,697][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:22:34,205][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:22:34,711][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:22:35,219][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:22:35,728][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:22:36,235][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:22:36,743][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:22:37,250][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:22:37,758][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:22:38,265][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:22:38,772][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:22:39,279][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:22:39,786][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:22:40,293][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:22:40,801][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:22:41,309][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:22:41,817][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:22:42,324][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:22:42,832][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:22:43,339][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:22:43,845][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:22:44,352][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:22:44,859][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:22:45,366][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:22:45,873][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:22:46,380][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:22:46,887][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:22:47,394][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:22:47,901][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:22:48,408][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:22:48,915][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:22:49,422][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:22:49,930][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:22:50,438][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:22:50,947][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:22:51,453][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:22:51,962][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:22:52,469][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:22:52,977][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:22:53,483][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 21:22:54,145][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.23%, ΔTime: 00:01:05 [2026-03-25 21:22:54,891][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:22:54,893][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:22:54,895][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:22:55,560][__main__][INFO] - Iteration 262 took 1m 15s (9.45% Gen, 89.67% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 57h 17m 30s. Estimated total time: 63h 5m 12s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 10s, 500 more iterations: 10h 30m 52s. [2026-03-25 21:22:55,562][__main__][INFO] - Starting iteration 262. [2026-03-25 21:22:55,963][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:22:55,964][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:22:56,594][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:23:02,406][__main__][INFO] - Number of regex retries in iteration 262: 1 [2026-03-25 21:23:02,407][__main__][INFO] - agents played in iteration 262 are Bob, Alice [2026-03-25 21:23:03,361][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:23:04,245][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:23:04,711][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:23:05,225][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:23:05,732][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:23:06,241][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:23:06,749][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:23:07,257][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:23:07,764][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:23:08,272][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:23:08,779][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:23:09,287][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:23:09,794][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:23:10,301][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:23:10,809][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:23:11,316][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:23:11,824][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:23:12,331][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:23:12,839][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:23:13,347][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:23:13,854][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:23:14,361][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:23:14,868][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:23:15,374][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:23:15,880][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:23:16,386][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:23:16,894][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:23:17,400][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:23:17,907][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:23:18,415][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:23:18,921][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:23:19,428][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:23:19,934][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:23:20,442][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:23:20,948][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:23:21,455][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:23:21,961][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:23:22,468][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:23:22,976][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:23:23,482][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:23:23,989][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:23:24,497][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:23:25,003][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:23:25,511][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:23:26,019][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:23:26,527][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:23:27,034][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:23:27,541][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:23:28,048][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:23:28,554][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:23:29,060][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:23:29,566][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:23:30,074][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:23:30,582][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:23:31,089][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:23:31,598][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:23:32,107][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:23:32,614][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:23:33,122][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:23:33,629][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:23:34,136][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:23:34,643][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:23:35,149][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:23:35,657][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:23:36,163][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:23:36,669][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:23:37,179][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:23:37,687][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:23:38,195][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:23:38,703][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:23:39,211][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:23:39,721][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:23:40,229][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:23:40,738][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:23:41,245][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:23:41,751][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:23:42,258][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:23:42,764][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:23:43,273][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:23:43,781][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:23:44,288][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:23:44,796][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:23:45,303][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:23:45,811][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:23:46,318][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:23:46,826][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:23:47,334][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:23:47,843][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:23:48,350][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:23:48,857][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:23:49,365][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:23:49,873][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:23:50,380][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:23:50,887][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:23:51,396][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:23:51,903][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:23:52,411][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:23:52,919][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:23:53,426][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:23:53,934][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:23:54,440][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:23:54,947][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:23:55,456][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:23:55,963][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:23:56,471][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:23:56,980][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:23:57,487][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:23:57,995][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:23:58,502][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:23:59,010][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:23:59,518][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:24:00,025][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:24:00,532][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:24:01,040][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:24:01,548][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:24:02,056][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:24:02,564][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:24:03,073][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:24:03,581][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:24:04,088][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:24:04,595][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:24:05,103][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:24:05,609][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:24:06,117][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:24:06,624][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:24:07,132][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:24:07,639][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:24:08,146][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:24:08,653][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:24:09,160][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 21:24:09,815][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-25 21:24:10,566][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:24:10,569][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:24:10,570][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:24:11,233][__main__][INFO] - Iteration 263 took 1m 15s (8.56% Gen, 90.56% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 54m 32s. Estimated total time: 62h 43m 29s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 26s, 500 more iterations: 10h 27m 14s. [2026-03-25 21:24:11,235][__main__][INFO] - Starting iteration 263. [2026-03-25 21:24:11,639][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:24:11,640][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:24:12,434][mllm.models.large_language_model_local][WARNING] - Response Proposer: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:24:17,451][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:24:18,517][__main__][INFO] - Number of regex retries in iteration 263: 2 [2026-03-25 21:24:18,518][__main__][INFO] - agents played in iteration 263 are Bob, Alice [2026-03-25 21:24:19,481][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:24:20,112][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:24:20,576][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:24:21,088][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:24:21,596][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:24:22,104][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:24:22,613][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:24:23,121][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:24:23,629][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:24:24,138][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:24:24,646][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:24:25,154][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:24:25,661][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:24:26,169][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:24:26,677][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:24:27,184][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:24:27,692][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:24:28,199][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:24:28,709][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:24:29,219][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:24:29,727][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:24:30,236][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:24:30,743][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:24:31,251][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:24:31,759][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:24:32,267][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:24:32,774][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:24:33,281][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:24:33,787][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:24:34,297][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:24:34,804][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:24:35,311][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:24:35,819][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:24:36,326][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:24:36,838][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:24:37,347][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:24:37,856][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:24:38,365][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:24:38,874][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:24:39,382][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:24:39,890][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:24:40,399][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:24:40,907][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:24:41,414][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:24:41,920][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:24:42,427][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:24:42,934][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:24:43,441][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:24:43,948][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:24:44,456][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:24:44,963][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:24:45,470][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:24:45,979][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:24:46,487][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:24:46,996][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:24:47,504][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:24:48,012][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:24:48,522][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:24:49,032][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:24:49,542][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:24:50,053][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:24:50,563][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:24:51,072][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:24:51,580][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:24:52,088][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:24:52,597][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:24:53,105][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:24:53,614][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:24:54,123][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:24:54,632][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:24:55,139][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:24:55,647][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:24:56,156][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:24:56,664][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:24:57,172][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:24:57,680][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:24:58,188][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:24:58,695][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:24:59,203][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:24:59,711][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:25:00,220][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:25:00,728][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:25:01,235][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:25:01,744][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:25:02,251][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:25:02,758][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:25:03,266][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:25:03,772][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:25:04,280][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:25:04,787][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:25:05,293][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:25:05,801][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:25:06,309][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:25:06,816][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:25:07,323][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:25:07,830][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:25:08,338][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:25:08,846][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:25:09,353][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:25:09,862][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:25:10,371][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:25:10,880][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:25:11,388][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:25:11,898][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:25:12,407][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:25:12,915][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:25:13,423][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:25:13,930][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:25:14,438][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:25:14,946][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:25:15,454][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:25:15,960][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:25:16,467][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:25:16,974][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:25:17,482][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:25:17,989][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:25:18,497][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:25:19,004][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:25:19,513][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:25:20,021][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:25:20,530][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:25:21,037][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:25:21,545][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:25:22,053][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:25:22,561][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:25:23,069][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:25:23,578][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:25:24,085][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:25:24,593][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:25:25,102][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 21:25:25,764][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:05 [2026-03-25 21:25:26,519][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:25:26,521][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:25:26,523][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:25:27,212][__main__][INFO] - Iteration 264 took 1m 15s (9.10% Gen, 89.99% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 57h 8m 25s. Estimated total time: 62h 58m 39s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 57s, 500 more iterations: 10h 29m 46s. [2026-03-25 21:25:27,214][__main__][INFO] - Starting iteration 264. [2026-03-25 21:25:27,616][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:25:27,617][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:25:34,287][__main__][INFO] - Number of regex retries in iteration 264: 0 [2026-03-25 21:25:34,288][__main__][INFO] - agents played in iteration 264 are Bob, Alice [2026-03-25 21:25:35,245][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:25:35,871][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:25:36,337][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:25:36,850][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:25:37,358][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:25:37,867][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:25:38,375][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:25:38,884][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:25:39,391][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:25:39,900][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:25:40,407][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:25:40,915][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:25:41,423][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:25:41,931][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:25:42,439][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:25:42,947][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:25:43,454][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:25:43,962][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:25:44,469][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:25:44,975][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:25:45,483][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:25:45,990][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:25:46,498][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:25:47,005][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:25:47,513][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:25:48,020][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:25:48,527][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:25:49,034][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:25:49,541][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:25:50,049][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:25:50,557][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:25:51,064][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:25:51,571][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:25:52,079][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:25:52,586][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:25:53,092][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:25:53,599][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:25:54,108][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:25:54,615][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:25:55,122][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:25:55,630][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:25:56,138][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:25:56,643][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:25:57,146][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:25:57,649][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:25:58,152][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:25:58,657][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:25:59,160][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:25:59,664][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:26:00,167][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:26:00,675][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:26:01,182][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:26:01,690][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:26:02,199][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:26:02,707][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:26:03,215][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:26:03,723][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:26:04,230][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:26:04,741][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:26:05,250][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:26:05,757][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:26:06,266][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:26:06,773][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:26:07,281][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:26:07,789][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:26:08,298][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:26:08,806][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:26:09,315][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:26:09,823][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:26:10,332][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:26:10,840][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:26:11,349][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:26:11,857][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:26:12,365][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:26:12,873][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:26:13,381][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:26:13,888][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:26:14,397][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:26:14,905][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:26:15,412][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:26:15,921][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:26:16,429][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:26:16,938][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:26:17,446][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:26:17,953][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:26:18,462][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:26:18,970][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:26:19,478][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:26:19,985][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:26:20,492][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:26:21,000][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:26:21,508][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:26:22,016][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:26:22,525][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:26:23,033][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:26:23,540][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:26:24,047][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:26:24,555][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:26:25,062][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:26:25,569][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:26:26,075][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:26:26,582][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:26:27,089][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:26:27,596][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:26:28,103][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:26:28,610][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:26:29,114][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:26:29,619][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:26:30,123][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:26:30,627][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:26:31,130][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:26:31,636][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:26:32,140][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:26:32,644][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:26:33,151][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:26:33,658][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:26:34,165][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:26:34,672][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:26:35,180][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:26:35,688][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:26:36,195][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:26:36,702][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:26:37,211][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:26:37,718][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:26:38,227][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:26:38,735][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:26:39,244][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:26:39,751][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:26:40,260][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:26:40,767][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 21:26:41,427][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-25 21:26:42,184][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:26:42,186][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:26:42,188][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:26:42,854][__main__][INFO] - Iteration 265 took 1m 15s (8.87% Gen, 90.25% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 50m 25s. Estimated total time: 62h 41m 55s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 23s, 500 more iterations: 10h 26m 59s. [2026-03-25 21:26:42,856][__main__][INFO] - Starting iteration 265. [2026-03-25 21:26:43,257][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:26:43,258][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:26:43,878][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:26:49,037][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:26:50,117][__main__][INFO] - Number of regex retries in iteration 265: 2 [2026-03-25 21:26:50,118][__main__][INFO] - agents played in iteration 265 are Bob, Alice [2026-03-25 21:26:51,081][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:26:51,705][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:26:52,168][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:26:52,680][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:26:53,187][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:26:53,695][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:26:54,202][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:26:54,710][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:26:55,218][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:26:55,728][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:26:56,233][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:26:56,740][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:26:57,246][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:26:57,752][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:26:58,257][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:26:58,763][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:26:59,268][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:26:59,773][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:27:00,280][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:27:00,786][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:27:01,292][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:27:01,799][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:27:02,305][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:27:02,811][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:27:03,318][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:27:03,826][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:27:04,334][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:27:04,840][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:27:05,347][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:27:05,857][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:27:06,363][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:27:06,872][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:27:07,379][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:27:07,886][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:27:08,392][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:27:08,900][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:27:09,407][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:27:09,915][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:27:10,423][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:27:10,930][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:27:11,438][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:27:11,945][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:27:12,453][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:27:12,961][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:27:13,468][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:27:13,977][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:27:14,484][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:27:14,992][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:27:15,500][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:27:16,007][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:27:16,515][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:27:17,023][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:27:17,530][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:27:18,038][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:27:18,547][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:27:19,054][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:27:19,562][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:27:20,069][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:27:20,576][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:27:21,082][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:27:21,588][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:27:22,097][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:27:22,604][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:27:23,111][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:27:23,618][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:27:24,126][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:27:24,634][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:27:25,142][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:27:25,649][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:27:26,157][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:27:26,665][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:27:27,174][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:27:27,681][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:27:28,189][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:27:28,695][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:27:29,201][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:27:29,706][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:27:30,212][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:27:30,720][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:27:31,228][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:27:31,733][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:27:32,241][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:27:32,749][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:27:33,256][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:27:33,762][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:27:34,269][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:27:34,777][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:27:35,283][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:27:35,789][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:27:36,296][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:27:36,804][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:27:37,311][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:27:37,819][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:27:38,327][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:27:38,835][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:27:39,342][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:27:39,850][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:27:40,358][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:27:40,866][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:27:41,373][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:27:41,879][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:27:42,387][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:27:42,895][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:27:43,402][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:27:43,908][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:27:44,418][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:27:44,926][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:27:45,433][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:27:45,940][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:27:46,446][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:27:46,953][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:27:47,460][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:27:47,967][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:27:48,476][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:27:48,983][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:27:49,490][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:27:49,998][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:27:50,506][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:27:51,013][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:27:51,521][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:27:52,028][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:27:52,537][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:27:53,044][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:27:53,548][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:27:54,055][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:27:54,562][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:27:55,069][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:27:55,575][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:27:56,082][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:27:56,588][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21744 tokens. [2026-03-25 21:27:57,238][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-25 21:27:57,987][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:27:57,989][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:27:57,990][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:27:58,654][__main__][INFO] - Iteration 266 took 1m 15s (9.10% Gen, 90.02% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 57m 7s. Estimated total time: 62h 49m 53s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 39s, 500 more iterations: 10h 28m 18s. [2026-03-25 21:27:58,656][__main__][INFO] - Starting iteration 266. [2026-03-25 21:27:59,060][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:27:59,060][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:27:59,678][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:28:00,770][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:28:05,852][__main__][INFO] - Number of regex retries in iteration 266: 2 [2026-03-25 21:28:05,853][__main__][INFO] - agents played in iteration 266 are Bob, Alice [2026-03-25 21:28:06,808][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:28:07,436][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:28:07,901][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:28:08,413][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:28:08,921][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:28:09,429][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:28:09,936][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:28:10,443][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:28:10,949][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:28:11,457][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:28:11,967][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:28:12,476][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:28:12,984][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:28:13,493][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:28:14,001][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:28:14,509][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:28:15,018][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:28:15,527][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:28:16,033][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:28:16,539][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:28:17,046][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:28:17,552][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:28:18,058][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:28:18,565][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:28:19,070][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:28:19,578][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:28:20,086][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:28:20,594][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:28:21,103][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:28:21,611][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:28:22,120][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:28:22,629][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:28:23,138][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:28:23,647][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:28:24,154][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:28:24,662][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:28:25,169][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:28:25,676][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:28:26,183][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:28:26,689][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:28:27,197][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:28:27,704][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:28:28,210][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:28:28,747][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:28:29,253][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:28:29,759][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:28:30,266][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:28:30,772][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:28:31,277][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:28:31,783][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:28:32,289][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:28:32,798][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:28:33,305][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:28:33,812][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:28:34,319][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:28:34,827][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:28:35,335][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:28:35,842][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:28:36,350][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:28:36,858][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:28:37,367][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:28:37,875][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:28:38,382][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:28:38,890][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:28:39,398][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:28:39,906][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:28:40,413][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:28:40,922][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:28:41,429][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:28:41,937][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:28:42,445][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:28:42,953][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:28:43,460][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:28:43,968][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:28:44,477][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:28:44,985][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:28:45,493][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:28:46,002][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:28:46,509][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:28:47,019][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:28:47,527][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:28:48,035][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:28:48,543][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:28:49,050][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:28:49,557][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:28:50,063][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:28:50,569][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:28:51,077][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:28:51,583][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:28:52,090][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:28:52,601][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:28:53,110][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:28:53,618][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:28:54,128][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:28:54,637][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:28:55,145][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:28:55,653][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:28:56,161][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:28:56,669][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:28:57,178][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:28:57,685][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:28:58,191][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:28:58,698][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:28:59,206][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:28:59,713][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:29:00,221][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:29:00,727][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:29:01,233][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:29:01,740][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:29:02,246][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:29:02,753][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:29:03,260][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:29:03,768][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:29:04,274][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:29:04,781][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:29:05,288][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:29:05,794][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:29:06,301][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:29:06,808][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:29:07,317][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:29:07,824][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:29:08,331][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:29:08,840][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:29:09,348][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:29:09,856][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:29:10,364][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:29:10,873][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:29:11,381][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:29:11,889][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:29:12,397][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 21:29:13,060][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 21:29:13,816][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:29:13,818][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:29:13,820][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:29:14,485][__main__][INFO] - Iteration 267 took 1m 15s (9.01% Gen, 90.11% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 57m 16s. Estimated total time: 62h 51m 18s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 42s, 500 more iterations: 10h 28m 33s. [2026-03-25 21:29:14,491][__main__][INFO] - Starting iteration 267. [2026-03-25 21:29:14,892][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:29:14,893][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:29:21,531][__main__][INFO] - Number of regex retries in iteration 267: 0 [2026-03-25 21:29:21,532][__main__][INFO] - agents played in iteration 267 are Bob, Alice [2026-03-25 21:29:22,500][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:29:23,127][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:29:23,590][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:29:24,102][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:29:24,610][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:29:25,118][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:29:25,625][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:29:26,134][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:29:26,641][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:29:27,149][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:29:27,660][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:29:28,169][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:29:28,678][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:29:29,187][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:29:29,697][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:29:30,207][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:29:30,715][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:29:31,224][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:29:31,733][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:29:32,242][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:29:32,751][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:29:33,260][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:29:33,767][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:29:34,275][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:29:34,782][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:29:35,289][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:29:35,798][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:29:36,306][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:29:36,815][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:29:37,324][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:29:37,832][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:29:38,340][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:29:38,848][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:29:39,357][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:29:39,865][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:29:40,372][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:29:40,880][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:29:41,388][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:29:41,898][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:29:42,406][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:29:42,913][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:29:43,422][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:29:43,930][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:29:44,436][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:29:44,944][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:29:45,451][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:29:45,958][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:29:46,465][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:29:46,971][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:29:47,479][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:29:47,986][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:29:48,492][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:29:48,999][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:29:49,506][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:29:50,012][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:29:50,518][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:29:51,025][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:29:51,532][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:29:52,040][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:29:52,549][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:29:53,057][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:29:53,565][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:29:54,073][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:29:54,581][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:29:55,089][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:29:55,598][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:29:56,107][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:29:56,614][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:29:57,121][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:29:57,630][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:29:58,139][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:29:58,647][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:29:59,153][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:29:59,661][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:30:00,170][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:30:00,679][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:30:01,187][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:30:01,697][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:30:02,206][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:30:02,715][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:30:03,225][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:30:03,734][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:30:04,241][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:30:04,749][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:30:05,258][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:30:05,766][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:30:06,274][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:30:06,780][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:30:07,287][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:30:07,795][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:30:08,303][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:30:08,811][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:30:09,320][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:30:09,830][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:30:10,338][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:30:10,847][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:30:11,357][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:30:11,865][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:30:12,373][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:30:12,881][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:30:13,389][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:30:13,897][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:30:14,406][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:30:14,915][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:30:15,423][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:30:15,931][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:30:16,438][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:30:16,945][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:30:17,452][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:30:17,958][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:30:18,464][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:30:18,971][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:30:19,479][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:30:19,986][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:30:20,492][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:30:20,999][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:30:21,505][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:30:22,013][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:30:22,520][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:30:23,027][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:30:23,535][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:30:24,043][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:30:24,551][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:30:25,060][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:30:25,568][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:30:26,077][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:30:26,585][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:30:27,094][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:30:27,602][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:30:28,111][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 21:30:28,777][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 21:30:29,545][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:30:29,548][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:30:29,549][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:30:30,571][__main__][INFO] - Iteration 268 took 1m 15s (8.77% Gen, 89.87% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 57h 8m 42s. Estimated total time: 63h 4m 0s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 8s, 500 more iterations: 10h 30m 40s. [2026-03-25 21:30:30,573][__main__][INFO] - Starting iteration 268. [2026-03-25 21:30:30,976][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:30:30,977][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:30:31,593][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:30:38,081][__main__][INFO] - Number of regex retries in iteration 268: 1 [2026-03-25 21:30:38,082][__main__][INFO] - agents played in iteration 268 are Bob, Alice [2026-03-25 21:30:39,038][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:30:39,672][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:30:40,137][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:30:40,651][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:30:41,159][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:30:41,666][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:30:42,173][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:30:42,681][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:30:43,188][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:30:43,697][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:30:44,205][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:30:44,712][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:30:45,221][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:30:45,730][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:30:46,238][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:30:46,745][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:30:47,252][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:30:47,760][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:30:48,267][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:30:48,775][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:30:49,282][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:30:49,790][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:30:50,298][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:30:50,805][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:30:51,313][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:30:51,821][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:30:52,331][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:30:52,840][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:30:53,348][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:30:53,857][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:30:54,365][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:30:54,874][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:30:55,382][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:30:55,890][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:30:56,398][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:30:56,906][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:30:57,413][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:30:57,921][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:30:58,428][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:30:58,936][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:30:59,443][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:30:59,951][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:31:00,460][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:31:00,969][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:31:01,478][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:31:01,986][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:31:02,494][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:31:03,002][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:31:03,510][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:31:04,019][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:31:04,527][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:31:05,039][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:31:05,548][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:31:06,056][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:31:06,564][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:31:07,073][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:31:07,582][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:31:08,091][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:31:08,599][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:31:09,107][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:31:09,615][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:31:10,123][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:31:10,631][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:31:11,139][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:31:11,648][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:31:12,156][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:31:12,663][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:31:13,170][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:31:13,678][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:31:14,186][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:31:14,694][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:31:15,202][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:31:15,710][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:31:16,219][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:31:16,728][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:31:17,237][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:31:17,746][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:31:18,254][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:31:18,763][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:31:19,272][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:31:19,780][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:31:20,288][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:31:20,798][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:31:21,306][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:31:21,814][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:31:22,322][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:31:22,831][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:31:23,347][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:31:23,856][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:31:24,364][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:31:24,873][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:31:25,382][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:31:25,890][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:31:26,399][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:31:26,908][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:31:27,417][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:31:27,926][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:31:28,435][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:31:28,943][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:31:29,450][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:31:29,959][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:31:30,467][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:31:30,975][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:31:31,482][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:31:31,990][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:31:32,499][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:31:33,008][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:31:33,518][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:31:34,028][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:31:34,538][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:31:35,048][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:31:35,559][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:31:36,068][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:31:36,577][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:31:37,085][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:31:37,595][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:31:38,104][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:31:38,612][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:31:39,122][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:31:39,631][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:31:40,140][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:31:40,649][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:31:41,158][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:31:41,666][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:31:42,173][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:31:42,681][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:31:43,189][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:31:43,698][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:31:44,206][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:31:44,714][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 21:31:45,381][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 21:31:46,155][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:31:46,158][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:31:46,159][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:31:46,830][__main__][INFO] - Iteration 269 took 1m 15s (9.37% Gen, 89.75% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 57h 16m 12s. Estimated total time: 63h 12m 46s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 25s, 500 more iterations: 10h 32m 7s. [2026-03-25 21:31:46,833][__main__][INFO] - Starting iteration 269. [2026-03-25 21:31:47,235][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:31:47,235][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:31:50,398][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:31:51,528][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:31:53,700][__main__][INFO] - Number of regex retries in iteration 269: 2 [2026-03-25 21:31:53,701][__main__][INFO] - agents played in iteration 269 are Bob, Alice [2026-03-25 21:31:54,662][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:31:55,296][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:31:55,760][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:31:56,273][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:31:56,781][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:31:57,288][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:31:57,797][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:31:58,304][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:31:58,812][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:31:59,319][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:31:59,830][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:32:00,340][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:32:00,849][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:32:01,357][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:32:01,865][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:32:02,374][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:32:02,881][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:32:03,387][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:32:03,897][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:32:04,407][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:32:04,916][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:32:05,425][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:32:05,933][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:32:06,441][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:32:06,950][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:32:07,459][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:32:07,987][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:32:08,501][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:32:09,010][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:32:09,520][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:32:10,030][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:32:10,539][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:32:11,048][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:32:11,558][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:32:12,067][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:32:12,576][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:32:13,085][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:32:13,593][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:32:14,102][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:32:14,610][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:32:15,119][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:32:15,627][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:32:16,140][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:32:16,652][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:32:17,162][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:32:17,675][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:32:18,185][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:32:18,698][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:32:19,210][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:32:19,721][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:32:20,232][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:32:20,741][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:32:21,249][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:32:21,759][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:32:22,268][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:32:22,777][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:32:23,285][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:32:23,793][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:32:24,302][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:32:24,810][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:32:25,319][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:32:25,827][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:32:26,336][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:32:26,845][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:32:27,353][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:32:27,862][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:32:28,369][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:32:28,874][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:32:29,380][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:32:29,888][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:32:30,397][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:32:30,905][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:32:31,412][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:32:31,918][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:32:32,425][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:32:32,932][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:32:33,439][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:32:33,946][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:32:34,454][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:32:34,961][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:32:35,467][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:32:35,976][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:32:36,483][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:32:36,992][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:32:37,499][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:32:38,008][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:32:38,516][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:32:39,024][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:32:39,531][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:32:40,039][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:32:40,548][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:32:41,056][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:32:41,564][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:32:42,073][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:32:42,582][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:32:43,090][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:32:43,601][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:32:44,111][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:32:44,620][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:32:45,128][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:32:45,636][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:32:46,144][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:32:46,651][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:32:47,159][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:32:47,667][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:32:48,175][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:32:48,685][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:32:49,196][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:32:49,707][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:32:50,217][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:32:50,727][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:32:51,237][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:32:51,748][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:32:52,258][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:32:52,765][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:32:53,272][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:32:53,779][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:32:54,287][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:32:54,795][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:32:55,303][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:32:55,850][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:32:56,359][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:32:56,867][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:32:57,374][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:32:57,882][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:32:58,390][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:32:58,898][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:32:59,407][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:32:59,915][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:33:00,460][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 21:33:01,109][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:05 [2026-03-25 21:33:01,876][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:33:01,878][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:33:01,880][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:33:02,553][__main__][INFO] - Iteration 270 took 1m 15s (8.58% Gen, 90.52% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 48m 6s. Estimated total time: 62h 45m 55s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 31s, 500 more iterations: 10h 27m 39s. [2026-03-25 21:33:02,555][__main__][INFO] - Starting iteration 270. [2026-03-25 21:33:02,955][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:33:02,956][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:33:09,499][__main__][INFO] - Number of regex retries in iteration 270: 0 [2026-03-25 21:33:09,500][__main__][INFO] - agents played in iteration 270 are Bob, Alice [2026-03-25 21:33:10,457][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:33:11,094][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:33:11,559][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:33:12,071][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:33:12,579][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:33:13,087][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:33:13,594][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:33:14,102][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:33:14,610][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:33:15,119][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:33:15,626][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:33:16,132][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:33:16,640][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:33:17,147][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:33:17,654][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:33:18,161][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:33:18,668][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:33:19,175][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:33:19,685][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:33:20,193][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:33:20,702][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:33:21,211][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:33:21,720][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:33:22,228][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:33:22,738][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:33:23,247][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:33:23,755][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:33:24,263][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:33:24,770][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:33:25,278][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:33:25,786][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:33:26,294][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:33:26,802][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:33:27,310][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:33:27,817][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:33:28,324][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:33:28,830][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:33:29,337][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:33:29,844][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:33:30,350][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:33:30,857][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:33:31,364][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:33:31,872][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:33:32,380][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:33:32,888][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:33:33,396][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:33:33,903][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:33:34,410][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:33:34,919][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:33:35,427][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:33:35,935][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:33:36,442][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:33:36,949][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:33:37,457][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:33:37,964][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:33:38,471][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:33:38,979][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:33:39,488][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:33:39,999][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:33:40,508][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:33:41,018][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:33:41,528][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:33:42,037][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:33:42,545][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:33:43,054][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:33:43,563][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:33:44,070][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:33:44,579][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:33:45,087][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:33:45,595][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:33:46,103][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:33:46,610][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:33:47,118][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:33:47,626][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:33:48,133][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:33:48,639][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:33:49,146][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:33:49,652][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:33:50,159][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:33:50,666][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:33:51,173][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:33:51,679][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:33:52,187][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:33:52,696][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:33:53,204][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:33:53,712][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:33:54,220][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:33:54,729][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:33:55,237][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:33:55,746][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:33:56,253][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:33:56,761][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:33:57,268][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:33:57,777][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:33:58,284][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:33:58,792][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:33:59,299][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:33:59,807][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:34:00,314][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:34:00,821][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:34:01,327][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:34:01,833][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:34:02,339][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:34:02,849][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:34:03,355][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:34:03,861][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:34:04,367][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:34:04,875][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:34:05,382][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:34:05,889][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:34:06,397][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:34:06,905][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:34:07,412][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:34:07,923][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:34:08,431][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:34:08,939][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:34:09,448][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:34:09,957][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:34:10,464][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:34:10,972][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:34:11,479][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:34:11,987][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:34:12,497][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:34:13,010][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:34:13,518][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:34:14,027][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:34:14,537][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:34:15,045][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:34:15,553][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:34:16,062][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 21:34:16,730][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.65%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 21:34:17,500][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:34:17,503][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:34:17,507][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:34:18,202][__main__][INFO] - Iteration 271 took 1m 15s (8.70% Gen, 90.38% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 43m 16s. Estimated total time: 62h 42m 21s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 24s, 500 more iterations: 10h 27m 3s. [2026-03-25 21:34:18,204][__main__][INFO] - Starting iteration 271. [2026-03-25 21:34:18,607][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:34:18,608][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:34:25,344][__main__][INFO] - Number of regex retries in iteration 271: 0 [2026-03-25 21:34:25,345][__main__][INFO] - agents played in iteration 271 are Bob, Alice [2026-03-25 21:34:26,316][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:34:26,939][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:34:27,404][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:34:27,918][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:34:28,427][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:34:28,935][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:34:29,447][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:34:29,955][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:34:30,463][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:34:30,970][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:34:31,479][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:34:31,986][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:34:32,497][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:34:33,005][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:34:33,513][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:34:34,020][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:34:34,529][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:34:35,038][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:34:35,550][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:34:36,058][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:34:36,565][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:34:37,072][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:34:37,580][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:34:38,088][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:34:38,595][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:34:39,105][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:34:39,613][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:34:40,123][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:34:40,630][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:34:41,139][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:34:41,647][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:34:42,154][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:34:42,662][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:34:43,169][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:34:43,675][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:34:44,183][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:34:44,689][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:34:45,199][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:34:45,706][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:34:46,213][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:34:46,720][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:34:47,228][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:34:47,737][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:34:48,244][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:34:48,751][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:34:49,259][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:34:49,773][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:34:50,280][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:34:50,788][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:34:51,297][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:34:51,805][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:34:52,313][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:34:52,823][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:34:53,332][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:34:53,841][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:34:54,352][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:34:54,859][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:34:55,367][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:34:55,875][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:34:56,382][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:34:56,890][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:34:57,398][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:34:57,905][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:34:58,413][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:34:58,921][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:34:59,430][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:34:59,939][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:35:00,445][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:35:00,954][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:35:01,462][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:35:01,970][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:35:02,478][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:35:02,986][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:35:03,493][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:35:04,003][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:35:04,512][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:35:05,020][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:35:05,529][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:35:06,037][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:35:06,545][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:35:07,053][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:35:07,561][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:35:08,067][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:35:08,575][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:35:09,082][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:35:09,590][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:35:10,097][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:35:10,604][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:35:11,111][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:35:11,618][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:35:12,126][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:35:12,634][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:35:13,142][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:35:13,650][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:35:14,157][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:35:14,669][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:35:15,176][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:35:15,684][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:35:16,191][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:35:16,699][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:35:17,205][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:35:17,713][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:35:18,221][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:35:18,728][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:35:19,236][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:35:19,745][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:35:20,252][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:35:20,759][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:35:21,266][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:35:21,772][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:35:22,279][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:35:22,786][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:35:23,293][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:35:23,800][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:35:24,307][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:35:24,818][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:35:25,325][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:35:25,834][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:35:26,340][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:35:26,848][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:35:27,355][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:35:27,863][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:35:28,369][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:35:28,877][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:35:29,384][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:35:29,915][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:35:30,423][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:35:30,931][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:35:31,438][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:35:31,946][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 21:35:32,604][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-25 21:35:33,370][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:35:33,373][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:35:33,374][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:35:34,052][__main__][INFO] - Iteration 272 took 1m 15s (8.93% Gen, 90.17% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 51m 53s. Estimated total time: 62h 52m 14s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 44s, 500 more iterations: 10h 28m 42s. [2026-03-25 21:35:34,054][__main__][INFO] - Starting iteration 272. [2026-03-25 21:35:34,454][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:35:34,455][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:35:40,945][__main__][INFO] - Number of regex retries in iteration 272: 0 [2026-03-25 21:35:40,946][__main__][INFO] - agents played in iteration 272 are Bob, Alice [2026-03-25 21:35:41,913][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:35:42,544][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:35:43,004][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:35:43,519][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:35:44,025][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:35:44,532][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:35:45,039][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:35:45,545][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:35:46,052][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:35:46,557][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:35:47,069][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:35:47,578][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:35:48,086][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:35:48,593][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:35:49,102][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:35:49,611][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:35:50,121][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:35:50,629][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:35:51,137][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:35:51,645][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:35:52,152][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:35:52,660][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:35:53,167][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:35:53,675][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:35:54,182][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:35:54,689][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:35:55,200][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:35:55,709][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:35:56,219][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:35:56,728][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:35:57,237][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:35:57,746][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:35:58,253][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:35:58,762][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:35:59,289][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:35:59,802][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:36:00,311][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:36:00,820][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:36:01,329][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:36:01,839][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:36:02,348][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:36:02,857][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:36:03,367][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:36:03,877][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:36:04,386][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:36:04,894][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:36:05,402][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:36:05,910][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:36:06,419][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:36:06,928][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:36:07,439][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:36:07,949][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:36:08,458][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:36:08,967][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:36:09,476][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:36:09,984][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:36:10,494][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:36:11,002][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:36:11,510][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:36:12,018][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:36:12,526][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:36:13,035][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:36:13,542][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:36:14,050][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:36:14,559][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:36:15,067][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:36:15,572][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:36:16,077][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:36:16,584][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:36:17,090][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:36:17,597][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:36:18,103][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:36:18,609][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:36:19,115][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:36:19,624][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:36:20,133][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:36:20,641][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:36:21,149][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:36:21,658][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:36:22,166][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:36:22,674][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:36:23,182][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:36:23,689][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:36:24,197][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:36:24,704][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:36:25,210][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:36:25,718][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:36:26,225][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:36:26,732][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:36:27,239][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:36:27,747][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:36:28,256][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:36:28,764][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:36:29,272][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:36:29,781][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:36:30,289][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:36:30,797][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:36:31,305][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:36:31,813][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:36:32,322][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:36:32,831][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:36:33,340][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:36:33,850][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:36:34,357][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:36:34,865][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:36:35,374][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:36:35,882][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:36:36,390][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:36:36,898][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:36:37,407][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:36:37,916][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:36:38,425][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:36:38,933][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:36:39,442][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:36:39,951][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:36:40,461][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:36:40,969][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:36:41,479][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:36:41,988][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:36:42,497][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:36:43,005][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:36:43,514][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:36:44,022][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:36:44,529][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:36:45,038][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:36:45,546][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:36:46,053][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:36:46,562][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:36:47,070][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:36:47,577][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21733 tokens. [2026-03-25 21:36:48,237][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 21:36:48,999][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:36:49,001][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:36:49,003][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:36:49,718][__main__][INFO] - Iteration 273 took 1m 15s (8.62% Gen, 90.42% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 41m 37s. Estimated total time: 62h 43m 13s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 26s, 500 more iterations: 10h 27m 12s. [2026-03-25 21:36:49,720][__main__][INFO] - Starting iteration 273. [2026-03-25 21:36:50,121][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:36:50,121][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:36:50,764][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:36:57,005][__main__][INFO] - Number of regex retries in iteration 273: 1 [2026-03-25 21:36:57,006][__main__][INFO] - agents played in iteration 273 are Bob, Alice [2026-03-25 21:36:57,951][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:36:58,584][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:36:59,050][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:36:59,563][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:37:00,069][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:37:00,579][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:37:01,088][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:37:01,598][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:37:02,109][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:37:02,619][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:37:03,127][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:37:03,633][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:37:04,141][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:37:04,648][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:37:05,155][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:37:05,662][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:37:06,169][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:37:06,677][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:37:07,186][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:37:07,693][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:37:08,203][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:37:08,713][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:37:09,222][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:37:09,730][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:37:10,238][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:37:10,746][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:37:11,254][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:37:11,761][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:37:12,267][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:37:12,775][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:37:13,281][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:37:13,788][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:37:14,296][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:37:14,803][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:37:15,311][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:37:15,821][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:37:16,329][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:37:16,837][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:37:17,344][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:37:17,853][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:37:18,361][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:37:18,868][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:37:19,377][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:37:19,885][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:37:20,393][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:37:20,901][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:37:21,410][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:37:21,921][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:37:22,430][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:37:22,937][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:37:23,445][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:37:23,953][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:37:24,461][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:37:24,968][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:37:25,475][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:37:25,983][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:37:26,490][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:37:26,999][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:37:27,507][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:37:28,016][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:37:28,525][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:37:29,033][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:37:29,541][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:37:30,050][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:37:30,558][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:37:31,067][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:37:31,579][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:37:32,088][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:37:32,596][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:37:33,105][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:37:33,614][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:37:34,124][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:37:34,632][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:37:35,140][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:37:35,647][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:37:36,154][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:37:36,660][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:37:37,167][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:37:37,673][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:37:38,181][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:37:38,687][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:37:39,193][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:37:39,702][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:37:40,209][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:37:40,716][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:37:41,224][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:37:41,731][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:37:42,239][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:37:42,748][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:37:43,254][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:37:43,762][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:37:44,269][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:37:44,775][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:37:45,281][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:37:45,788][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:37:46,296][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:37:46,802][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:37:47,308][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:37:47,817][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:37:48,326][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:37:48,833][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:37:49,341][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:37:49,849][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:37:50,357][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:37:50,863][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:37:51,370][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:37:51,878][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:37:52,386][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:37:52,893][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:37:53,401][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:37:53,910][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:37:54,418][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:37:54,926][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:37:55,434][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:37:55,941][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:37:56,448][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:37:56,956][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:37:57,463][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:37:57,970][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:37:58,477][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:37:58,984][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:37:59,491][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:38:00,002][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:38:00,511][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:38:01,019][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:38:01,528][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:38:02,039][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:38:02,547][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:38:03,056][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:38:03,565][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 21:38:04,226][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:05 [2026-03-25 21:38:04,995][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:38:04,997][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:38:04,999][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:38:05,671][__main__][INFO] - Iteration 274 took 1m 15s (9.11% Gen, 90.00% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 54m 41s. Estimated total time: 62h 57m 33s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 55s, 500 more iterations: 10h 29m 35s. [2026-03-25 21:38:05,673][__main__][INFO] - Starting iteration 274. [2026-03-25 21:38:06,076][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:38:06,077][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:38:06,688][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:38:12,599][__main__][INFO] - Number of regex retries in iteration 274: 1 [2026-03-25 21:38:12,893][__main__][INFO] - agents played in iteration 274 are Bob, Alice [2026-03-25 21:38:13,853][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:38:14,483][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:38:14,945][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:38:15,457][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:38:15,963][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:38:16,470][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:38:16,977][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:38:17,483][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:38:17,989][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:38:18,496][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:38:19,006][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:38:19,512][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:38:20,021][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:38:20,530][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:38:21,037][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:38:21,545][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:38:22,053][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:38:22,560][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:38:23,071][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:38:23,580][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:38:24,087][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:38:24,595][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:38:25,103][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:38:25,611][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:38:26,120][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:38:26,628][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:38:27,137][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:38:27,645][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:38:28,153][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:38:28,661][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:38:29,169][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:38:29,679][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:38:30,188][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:38:30,695][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:38:31,204][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:38:31,711][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:38:32,219][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:38:32,727][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:38:33,234][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:38:33,743][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:38:34,251][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:38:34,759][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:38:35,286][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:38:35,799][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:38:36,308][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:38:36,818][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:38:37,327][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:38:37,836][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:38:38,345][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:38:38,854][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:38:39,362][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:38:39,869][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:38:40,377][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:38:40,885][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:38:41,393][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:38:41,901][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:38:42,410][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:38:42,920][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:38:43,427][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:38:43,933][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:38:44,440][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:38:44,947][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:38:45,454][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:38:45,960][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:38:46,466][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:38:46,972][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:38:47,480][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:38:47,987][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:38:48,494][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:38:49,002][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:38:49,510][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:38:50,017][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:38:50,524][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:38:51,031][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:38:51,540][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:38:52,047][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:38:52,555][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:38:53,062][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:38:53,570][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:38:54,077][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:38:54,585][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:38:55,093][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:38:55,602][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:38:56,110][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:38:56,620][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:38:57,128][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:38:57,637][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:38:58,146][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:38:58,653][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:38:59,162][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:38:59,670][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:39:00,178][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:39:00,686][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:39:01,194][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:39:01,702][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:39:02,209][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:39:02,720][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:39:03,229][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:39:03,736][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:39:04,244][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:39:04,751][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:39:05,260][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:39:05,767][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:39:06,274][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:39:06,782][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:39:07,290][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:39:07,799][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:39:08,307][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:39:08,818][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:39:09,326][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:39:09,835][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:39:10,344][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:39:10,853][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:39:11,360][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:39:11,868][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:39:12,377][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:39:12,885][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:39:13,392][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:39:13,900][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:39:14,408][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:39:14,917][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:39:15,426][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:39:15,932][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:39:16,440][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:39:16,947][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:39:17,454][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:39:17,960][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:39:18,467][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:39:18,974][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:39:19,480][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-25 21:39:20,135][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 21:39:20,890][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:39:20,892][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:39:20,894][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:39:21,562][__main__][INFO] - Iteration 275 took 1m 15s (9.03% Gen, 90.08% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 50m 9s. Estimated total time: 62h 54m 18s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 48s, 500 more iterations: 10h 29m 3s. [2026-03-25 21:39:21,564][__main__][INFO] - Starting iteration 275. [2026-03-25 21:39:21,964][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:39:21,965][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:39:22,604][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:39:23,646][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:39:29,014][__main__][INFO] - Number of regex retries in iteration 275: 2 [2026-03-25 21:39:29,015][__main__][INFO] - agents played in iteration 275 are Bob, Alice [2026-03-25 21:39:29,986][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:39:30,611][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:39:31,074][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:39:31,586][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:39:32,094][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:39:32,602][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:39:33,108][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:39:33,616][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:39:34,124][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:39:34,631][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:39:35,142][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:39:35,651][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:39:36,160][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:39:36,668][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:39:37,177][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:39:37,685][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:39:38,193][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:39:38,703][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:39:39,211][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:39:39,719][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:39:40,226][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:39:40,733][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:39:41,240][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:39:41,748][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:39:42,254][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:39:42,762][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:39:43,271][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:39:43,779][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:39:44,286][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:39:44,794][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:39:45,303][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:39:45,810][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:39:46,319][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:39:46,829][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:39:47,336][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:39:47,844][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:39:48,350][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:39:48,859][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:39:49,366][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:39:49,873][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:39:50,380][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:39:50,888][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:39:51,395][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:39:51,903][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:39:52,410][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:39:52,919][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:39:53,427][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:39:53,935][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:39:54,442][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:39:54,950][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:39:55,457][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:39:55,965][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:39:56,472][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:39:56,980][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:39:57,487][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:39:57,994][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:39:58,501][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:39:59,009][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:39:59,517][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:40:00,026][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:40:00,534][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:40:01,042][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:40:01,550][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:40:02,060][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:40:02,568][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:40:03,078][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:40:03,585][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:40:04,093][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:40:04,600][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:40:05,109][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:40:05,615][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:40:06,123][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:40:06,629][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:40:07,138][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:40:07,646][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:40:08,153][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:40:08,662][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:40:09,170][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:40:09,679][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:40:10,187][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:40:10,695][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:40:11,203][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:40:11,710][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:40:12,219][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:40:12,727][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:40:13,235][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:40:13,743][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:40:14,251][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:40:14,759][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:40:15,266][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:40:15,774][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:40:16,283][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:40:16,791][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:40:17,299][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:40:17,807][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:40:18,317][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:40:18,827][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:40:19,336][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:40:19,845][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:40:20,353][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:40:20,860][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:40:21,368][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:40:21,875][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:40:22,383][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:40:22,891][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:40:23,398][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:40:23,906][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:40:24,414][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:40:24,922][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:40:25,430][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:40:25,939][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:40:26,447][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:40:26,955][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:40:27,463][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:40:27,970][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:40:28,478][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:40:28,986][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:40:29,493][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:40:30,000][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:40:30,508][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:40:31,015][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:40:31,523][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:40:32,031][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:40:32,540][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:40:33,049][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:40:33,558][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:40:34,066][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:40:34,575][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:40:35,083][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:40:35,590][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 21:40:36,253][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 21:40:37,019][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:40:37,022][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:40:37,023][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:40:37,700][__main__][INFO] - Iteration 276 took 1m 15s (9.31% Gen, 89.80% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 57h 1m 25s. Estimated total time: 63h 6m 50s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 13s, 500 more iterations: 10h 31m 8s. [2026-03-25 21:40:37,702][__main__][INFO] - Starting iteration 276. [2026-03-25 21:40:38,105][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:40:38,105][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:40:43,036][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:40:45,300][__main__][INFO] - Number of regex retries in iteration 276: 1 [2026-03-25 21:40:45,301][__main__][INFO] - agents played in iteration 276 are Bob, Alice [2026-03-25 21:40:46,263][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:40:46,902][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:40:47,366][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:40:47,880][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:40:48,388][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:40:48,892][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:40:49,403][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:40:49,911][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:40:50,420][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:40:50,928][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:40:51,441][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:40:51,949][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:40:52,458][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:40:52,966][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:40:53,473][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:40:53,982][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:40:54,490][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:40:55,001][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:40:55,510][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:40:56,018][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:40:56,527][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:40:57,036][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:40:57,546][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:40:58,054][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:40:58,562][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:40:59,070][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:40:59,578][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:41:00,085][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:41:00,592][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:41:01,100][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:41:01,608][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:41:02,116][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:41:02,623][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:41:03,131][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:41:03,637][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:41:04,144][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:41:04,651][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:41:05,159][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:41:05,665][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:41:06,172][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:41:06,679][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:41:07,186][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:41:07,693][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:41:08,200][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:41:08,706][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:41:09,214][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:41:09,721][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:41:10,229][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:41:10,735][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:41:11,242][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:41:11,751][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:41:12,258][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:41:12,766][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:41:13,275][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:41:13,782][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:41:14,291][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:41:14,800][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:41:15,308][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:41:15,820][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:41:16,326][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:41:16,832][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:41:17,341][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:41:17,850][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:41:18,360][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:41:18,867][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:41:19,375][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:41:19,881][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:41:20,387][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:41:20,893][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:41:21,401][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:41:21,907][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:41:22,414][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:41:22,922][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:41:23,429][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:41:23,937][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:41:24,445][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:41:24,952][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:41:25,460][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:41:25,967][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:41:26,474][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:41:26,981][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:41:27,488][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:41:27,996][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:41:28,503][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:41:29,009][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:41:29,517][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:41:30,023][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:41:30,531][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:41:31,038][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:41:31,545][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:41:32,052][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:41:32,559][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:41:33,067][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:41:33,574][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:41:34,081][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:41:34,589][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:41:35,096][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:41:35,603][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:41:36,111][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:41:36,618][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:41:37,126][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:41:37,633][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:41:38,141][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:41:38,649][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:41:39,155][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:41:39,663][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:41:40,170][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:41:40,676][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:41:41,181][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:41:41,686][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:41:42,193][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:41:42,700][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:41:43,207][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:41:43,716][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:41:44,226][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:41:44,735][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:41:45,244][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:41:45,754][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:41:46,264][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:41:46,773][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:41:47,282][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:41:47,790][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:41:48,299][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:41:48,809][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:41:49,322][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:41:49,833][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:41:50,343][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:41:50,853][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:41:51,363][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:41:51,874][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21735 tokens. [2026-03-25 21:41:52,551][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 21:41:53,315][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:41:53,317][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:41:53,319][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:41:54,225][__main__][INFO] - Iteration 277 took 1m 16s (9.45% Gen, 89.35% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 57h 19m 21s. Estimated total time: 63h 26m 2s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 52s, 500 more iterations: 10h 34m 20s. [2026-03-25 21:41:54,227][__main__][INFO] - Starting iteration 277. [2026-03-25 21:41:54,641][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:41:54,641][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:42:02,444][__main__][INFO] - Number of regex retries in iteration 277: 0 [2026-03-25 21:42:02,445][__main__][INFO] - agents played in iteration 277 are Bob, Alice [2026-03-25 21:42:03,424][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:42:04,060][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:42:04,527][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:42:05,041][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:42:05,551][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:42:06,061][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:42:06,571][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:42:07,079][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:42:07,588][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:42:08,098][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:42:08,608][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:42:09,117][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:42:09,626][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:42:10,135][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:42:10,643][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:42:11,151][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:42:11,660][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:42:12,168][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:42:12,676][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:42:13,182][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:42:13,689][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:42:14,197][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:42:14,704][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:42:15,210][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:42:15,718][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:42:16,226][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:42:16,735][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:42:17,243][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:42:17,751][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:42:18,259][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:42:18,767][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:42:19,275][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:42:19,783][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:42:20,291][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:42:20,799][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:42:21,307][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:42:21,815][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:42:22,323][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:42:22,830][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:42:23,340][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:42:23,848][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:42:24,357][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:42:24,865][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:42:25,372][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:42:25,880][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:42:26,389][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:42:26,898][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:42:27,406][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:42:27,914][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:42:28,422][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:42:28,930][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:42:29,439][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:42:29,948][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:42:30,456][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:42:30,964][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:42:31,471][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:42:31,979][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:42:32,486][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:42:32,994][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:42:33,502][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:42:34,011][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:42:34,521][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:42:35,029][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:42:35,538][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:42:36,047][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:42:36,556][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:42:37,065][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:42:37,574][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:42:38,083][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:42:38,591][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:42:39,100][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:42:39,609][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:42:40,117][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:42:40,626][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:42:41,135][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:42:41,643][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:42:42,151][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:42:42,660][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:42:43,169][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:42:43,677][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:42:44,184][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:42:44,693][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:42:45,199][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:42:45,706][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:42:46,212][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:42:46,721][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:42:47,228][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:42:47,735][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:42:48,242][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:42:48,748][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:42:49,256][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:42:49,764][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:42:50,270][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:42:50,782][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:42:51,290][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:42:51,799][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:42:52,306][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:42:52,815][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:42:53,322][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:42:53,830][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:42:54,335][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:42:54,841][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:42:55,348][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:42:55,854][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:42:56,361][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:42:56,868][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:42:57,376][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:42:57,884][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:42:58,390][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:42:58,901][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:42:59,409][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:42:59,917][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:43:00,425][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:43:00,934][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:43:01,479][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:43:01,988][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:43:02,496][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:43:03,005][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:43:03,513][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:43:04,022][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:43:04,531][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:43:05,040][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:43:05,549][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:43:06,060][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:43:06,570][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:43:07,081][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:43:07,589][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:43:08,099][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:43:08,608][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:43:09,119][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 21:43:09,792][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-25 21:43:10,555][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:43:10,558][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:43:10,559][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:43:11,251][__main__][INFO] - Iteration 278 took 1m 16s (10.19% Gen, 88.91% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 57h 42m 34s. Estimated total time: 63h 50m 32s. Time estimates for 10 more iterations: 12m 46s, 100 more iterations: 2h 7m 41s, 500 more iterations: 10h 38m 25s. [2026-03-25 21:43:11,255][__main__][INFO] - Starting iteration 278. [2026-03-25 21:43:11,660][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:43:11,661][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:43:12,859][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:43:18,637][__main__][INFO] - Number of regex retries in iteration 278: 1 [2026-03-25 21:43:18,637][__main__][INFO] - agents played in iteration 278 are Bob, Alice [2026-03-25 21:43:19,602][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:43:20,232][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:43:20,696][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:43:21,209][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:43:21,720][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:43:22,229][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:43:22,736][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:43:23,245][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:43:23,753][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:43:24,260][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:43:24,768][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:43:25,273][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:43:25,781][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:43:26,289][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:43:26,795][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:43:27,302][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:43:27,811][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:43:28,319][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:43:28,826][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:43:29,333][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:43:29,840][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:43:30,347][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:43:30,854][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:43:31,361][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:43:31,869][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:43:32,377][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:43:32,887][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:43:33,395][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:43:33,903][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:43:34,411][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:43:34,920][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:43:35,429][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:43:35,937][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:43:36,446][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:43:36,954][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:43:37,463][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:43:37,970][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:43:38,478][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:43:38,986][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:43:39,494][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:43:40,002][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:43:40,511][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:43:41,020][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:43:41,528][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:43:42,036][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:43:42,543][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:43:43,051][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:43:43,560][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:43:44,068][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:43:44,575][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:43:45,079][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:43:45,583][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:43:46,087][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:43:46,591][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:43:47,095][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:43:47,599][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:43:48,103][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:43:48,607][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:43:49,115][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:43:49,623][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:43:50,130][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:43:50,640][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:43:51,148][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:43:51,656][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:43:52,163][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:43:52,670][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:43:53,177][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:43:53,684][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:43:54,191][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:43:54,699][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:43:55,207][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:43:55,714][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:43:56,221][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:43:56,729][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:43:57,236][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:43:57,743][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:43:58,250][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:43:58,758][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:43:59,265][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:43:59,774][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:44:00,280][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:44:00,787][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:44:01,294][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:44:01,802][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:44:02,308][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:44:02,816][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:44:03,323][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:44:03,831][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:44:04,339][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:44:04,845][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:44:05,353][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:44:05,862][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:44:06,370][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:44:06,878][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:44:07,386][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:44:07,894][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:44:08,402][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:44:08,909][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:44:09,418][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:44:09,927][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:44:10,436][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:44:10,943][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:44:11,452][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:44:11,960][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:44:12,468][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:44:12,977][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:44:13,484][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:44:13,991][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:44:14,501][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:44:15,010][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:44:15,518][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:44:16,026][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:44:16,534][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:44:17,044][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:44:17,549][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:44:18,053][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:44:18,559][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:44:19,063][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:44:19,567][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:44:20,072][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:44:20,576][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:44:21,080][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:44:21,588][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:44:22,095][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:44:22,602][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:44:23,111][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:44:23,620][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:44:24,128][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:44:24,635][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:44:25,143][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 21:44:25,806][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 21:44:26,561][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:44:26,563][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:44:26,565][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:44:27,236][__main__][INFO] - Iteration 279 took 1m 15s (9.23% Gen, 89.88% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 49m 33s. Estimated total time: 62h 58m 47s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 57s, 500 more iterations: 10h 29m 47s. [2026-03-25 21:44:27,238][__main__][INFO] - Starting iteration 279. [2026-03-25 21:44:27,639][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:44:27,640][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:44:34,693][__main__][INFO] - Number of regex retries in iteration 279: 0 [2026-03-25 21:44:34,694][__main__][INFO] - agents played in iteration 279 are Bob, Alice [2026-03-25 21:44:35,656][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:44:36,291][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:44:36,756][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:44:37,270][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:44:37,778][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:44:38,285][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:44:38,794][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:44:39,302][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:44:39,811][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:44:40,320][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:44:40,827][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:44:41,334][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:44:41,840][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:44:42,348][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:44:42,855][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:44:43,362][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:44:43,868][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:44:44,374][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:44:44,883][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:44:45,390][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:44:45,897][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:44:46,405][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:44:46,913][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:44:47,420][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:44:47,928][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:44:48,435][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:44:48,944][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:44:49,452][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:44:49,960][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:44:50,468][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:44:50,978][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:44:51,486][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:44:51,994][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:44:52,501][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:44:53,013][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:44:53,521][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:44:54,030][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:44:54,541][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:44:55,050][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:44:55,559][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:44:56,068][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:44:56,577][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:44:57,085][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:44:57,591][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:44:58,099][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:44:58,605][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:44:59,113][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:44:59,620][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:45:00,127][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:45:00,634][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:45:01,141][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:45:01,648][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:45:02,156][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:45:02,663][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:45:03,170][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:45:03,677][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:45:04,184][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:45:04,691][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:45:05,200][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:45:05,709][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:45:06,219][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:45:06,728][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:45:07,237][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:45:07,745][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:45:08,253][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:45:08,762][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:45:09,270][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:45:09,777][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:45:10,285][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:45:10,793][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:45:11,300][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:45:11,808][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:45:12,316][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:45:12,824][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:45:13,332][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:45:13,838][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:45:14,345][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:45:14,851][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:45:15,357][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:45:15,863][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:45:16,369][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:45:16,877][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:45:17,384][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:45:17,891][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:45:18,398][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:45:18,905][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:45:19,413][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:45:19,921][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:45:20,428][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:45:20,937][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:45:21,444][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:45:21,952][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:45:22,461][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:45:22,968][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:45:23,476][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:45:23,984][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:45:24,493][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:45:25,001][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:45:25,509][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:45:26,019][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:45:26,528][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:45:27,038][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:45:27,547][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:45:28,056][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:45:28,566][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:45:29,075][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:45:29,582][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:45:30,089][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:45:30,595][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:45:31,102][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:45:31,608][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:45:32,115][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:45:32,623][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:45:33,131][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:45:33,637][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:45:34,143][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:45:34,649][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:45:35,156][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:45:35,662][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:45:36,168][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:45:36,675][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:45:37,181][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:45:37,688][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:45:38,197][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:45:38,705][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:45:39,215][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:45:39,723][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:45:40,231][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:45:40,742][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:45:41,251][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 21:45:41,911][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 21:45:42,662][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:45:42,664][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:45:42,665][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:45:43,332][__main__][INFO] - Iteration 280 took 1m 15s (9.32% Gen, 89.80% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 56h 54m 9s. Estimated total time: 63h 4m 39s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 9s, 500 more iterations: 10h 30m 46s. [2026-03-25 21:45:43,334][__main__][INFO] - Starting iteration 280. [2026-03-25 21:45:43,737][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:45:43,738][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:45:48,303][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:45:50,196][__main__][INFO] - Number of regex retries in iteration 280: 1 [2026-03-25 21:45:50,197][__main__][INFO] - agents played in iteration 280 are Bob, Alice [2026-03-25 21:45:51,139][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:45:52,045][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:45:52,510][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:45:53,023][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:45:53,530][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:45:54,041][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:45:54,549][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:45:55,056][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:45:55,564][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:45:56,072][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:45:56,579][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:45:57,086][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:45:57,592][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:45:58,101][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:45:58,609][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:45:59,115][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:45:59,623][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:46:00,130][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:46:00,641][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:46:01,149][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:46:01,656][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:46:02,165][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:46:02,673][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:46:03,181][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:46:03,688][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:46:04,199][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:46:04,710][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:46:05,221][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:46:05,729][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:46:06,239][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:46:06,749][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:46:07,258][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:46:07,766][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:46:08,274][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:46:08,782][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:46:09,289][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:46:09,798][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:46:10,305][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:46:10,811][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:46:11,321][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:46:11,829][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:46:12,338][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:46:12,846][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:46:13,355][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:46:13,864][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:46:14,373][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:46:14,880][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:46:15,389][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:46:15,898][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:46:16,408][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:46:16,917][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:46:17,427][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:46:17,936][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:46:18,446][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:46:18,954][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:46:19,463][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:46:19,972][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:46:20,480][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:46:20,988][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:46:21,496][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:46:22,003][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:46:22,510][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:46:23,018][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:46:23,526][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:46:24,033][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:46:24,539][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:46:25,046][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:46:25,555][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:46:26,063][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:46:26,571][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:46:27,081][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:46:27,589][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:46:28,097][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:46:28,605][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:46:29,113][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:46:29,620][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:46:30,128][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:46:30,634][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:46:31,141][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:46:31,647][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:46:32,155][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:46:32,661][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:46:33,169][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:46:33,677][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:46:34,184][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:46:34,691][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:46:35,201][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:46:35,709][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:46:36,217][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:46:36,726][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:46:37,235][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:46:37,744][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:46:38,253][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:46:38,763][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:46:39,272][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:46:39,781][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:46:40,289][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:46:40,802][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:46:41,311][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:46:41,819][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:46:42,328][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:46:42,836][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:46:43,345][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:46:43,852][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:46:44,360][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:46:44,868][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:46:45,378][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:46:45,886][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:46:46,394][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:46:46,903][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:46:47,411][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:46:47,920][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:46:48,429][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:46:48,939][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:46:49,449][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:46:49,958][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:46:50,466][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:46:50,975][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:46:51,484][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:46:51,992][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:46:52,501][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:46:53,010][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:46:53,519][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:46:54,027][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:46:54,534][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:46:55,042][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:46:55,549][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:46:56,056][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:46:56,563][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:46:57,070][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 21:46:57,722][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 21:46:58,483][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:46:58,485][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:46:58,487][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:46:59,154][__main__][INFO] - Iteration 281 took 1m 15s (8.56% Gen, 90.55% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 39m 7s. Estimated total time: 62h 50m 53s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 41s, 500 more iterations: 10h 28m 28s. [2026-03-25 21:46:59,156][__main__][INFO] - Starting iteration 281. [2026-03-25 21:46:59,560][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:46:59,561][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:47:06,797][__main__][INFO] - Number of regex retries in iteration 281: 0 [2026-03-25 21:47:06,797][__main__][INFO] - agents played in iteration 281 are Bob, Alice [2026-03-25 21:47:07,754][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:47:08,381][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:47:08,845][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:47:09,359][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:47:09,867][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:47:10,374][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:47:10,881][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:47:11,388][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:47:11,896][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:47:12,403][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:47:12,912][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:47:13,423][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:47:13,932][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:47:14,441][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:47:14,950][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:47:15,461][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:47:15,970][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:47:16,478][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:47:16,990][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:47:17,501][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:47:18,011][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:47:18,521][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:47:19,031][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:47:19,541][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:47:20,050][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:47:20,560][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:47:21,065][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:47:21,573][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:47:22,081][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:47:22,589][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:47:23,098][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:47:23,606][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:47:24,113][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:47:24,622][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:47:25,129][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:47:25,638][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:47:26,145][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:47:26,654][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:47:27,163][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:47:27,669][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:47:28,177][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:47:28,685][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:47:29,194][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:47:29,703][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:47:30,211][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:47:30,721][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:47:31,230][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:47:31,738][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:47:32,249][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:47:32,759][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:47:33,267][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:47:33,774][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:47:34,282][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:47:34,790][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:47:35,297][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:47:35,804][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:47:36,311][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:47:36,820][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:47:37,328][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:47:37,835][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:47:38,344][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:47:38,852][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:47:39,359][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:47:39,866][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:47:40,374][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:47:40,882][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:47:41,389][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:47:41,896][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:47:42,404][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:47:42,911][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:47:43,418][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:47:43,925][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:47:44,431][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:47:44,939][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:47:45,448][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:47:45,954][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:47:46,462][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:47:46,970][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:47:47,478][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:47:47,985][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:47:48,492][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:47:49,001][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:47:49,510][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:47:50,021][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:47:50,531][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:47:51,040][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:47:51,549][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:47:52,060][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:47:52,569][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:47:53,077][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:47:53,583][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:47:54,089][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:47:54,597][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:47:55,104][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:47:55,611][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:47:56,119][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:47:56,627][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:47:57,134][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:47:57,640][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:47:58,147][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:47:58,655][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:47:59,162][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:47:59,669][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:48:00,178][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:48:00,686][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:48:01,193][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:48:01,701][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:48:02,209][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:48:02,717][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:48:03,224][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:48:03,732][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:48:04,240][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:48:04,748][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:48:05,255][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:48:05,762][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:48:06,269][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:48:06,777][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:48:07,284][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:48:07,790][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:48:08,300][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:48:08,808][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:48:09,314][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:48:09,822][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:48:10,329][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:48:10,839][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:48:11,346][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:48:11,855][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:48:12,363][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:48:12,871][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:48:13,377][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21671 tokens. [2026-03-25 21:48:14,046][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 21:48:14,801][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:48:14,803][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:48:14,805][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:48:15,471][__main__][INFO] - Iteration 282 took 1m 15s (9.53% Gen, 89.59% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 57h 2m 35s. Estimated total time: 63h 15m 37s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 31s, 500 more iterations: 10h 32m 36s. [2026-03-25 21:48:15,473][__main__][INFO] - Starting iteration 282. [2026-03-25 21:48:15,875][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:48:15,876][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:48:16,491][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:48:21,676][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:48:22,753][__main__][INFO] - Number of regex retries in iteration 282: 2 [2026-03-25 21:48:22,754][__main__][INFO] - agents played in iteration 282 are Bob, Alice [2026-03-25 21:48:23,723][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:48:24,344][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:48:24,812][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:48:25,326][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:48:25,836][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:48:26,345][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:48:26,854][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:48:27,362][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:48:27,870][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:48:28,379][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:48:28,886][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:48:29,395][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:48:29,903][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:48:30,411][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:48:30,921][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:48:31,429][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:48:31,937][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:48:32,446][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:48:32,954][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:48:33,461][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:48:33,967][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:48:34,474][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:48:34,981][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:48:35,488][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:48:36,005][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:48:36,513][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:48:37,024][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:48:37,533][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:48:38,042][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:48:38,551][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:48:39,059][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:48:39,568][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:48:40,077][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:48:40,585][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:48:41,093][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:48:41,604][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:48:42,113][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:48:42,621][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:48:43,130][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:48:43,638][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:48:44,147][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:48:44,656][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:48:45,162][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:48:45,669][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:48:46,177][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:48:46,684][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:48:47,191][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:48:47,700][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:48:48,207][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:48:48,715][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:48:49,223][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:48:49,730][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:48:50,238][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:48:50,745][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:48:51,253][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:48:51,761][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:48:52,268][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:48:52,776][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:48:53,284][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:48:53,791][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:48:54,300][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:48:54,808][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:48:55,317][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:48:55,826][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:48:56,335][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:48:56,844][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:48:57,353][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:48:57,862][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:48:58,370][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:48:58,878][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:48:59,386][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:48:59,896][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:49:00,405][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:49:00,913][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:49:01,422][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:49:01,930][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:49:02,440][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:49:02,949][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:49:03,457][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:49:03,965][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:49:04,473][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:49:04,981][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:49:05,488][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:49:05,996][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:49:06,503][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:49:07,010][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:49:07,520][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:49:08,029][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:49:08,536][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:49:09,044][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:49:09,552][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:49:10,060][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:49:10,569][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:49:11,077][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:49:11,585][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:49:12,094][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:49:12,603][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:49:13,111][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:49:13,620][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:49:14,129][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:49:14,637][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:49:15,145][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:49:15,652][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:49:16,160][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:49:16,667][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:49:17,175][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:49:17,682][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:49:18,188][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:49:18,694][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:49:19,201][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:49:19,708][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:49:20,214][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:49:20,722][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:49:21,230][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:49:21,738][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:49:22,247][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:49:22,755][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:49:23,263][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:49:23,770][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:49:24,278][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:49:24,785][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:49:25,293][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:49:25,802][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:49:26,310][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:49:26,818][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:49:27,328][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:49:27,836][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:49:28,344][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:49:28,854][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:49:29,363][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 21:49:30,037][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-25 21:49:30,801][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:49:30,803][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:49:30,805][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:49:31,540][__main__][INFO] - Iteration 283 took 1m 15s (9.09% Gen, 89.94% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 48m 57s. Estimated total time: 63h 3m 16s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 6s, 500 more iterations: 10h 30m 32s. [2026-03-25 21:49:31,542][__main__][INFO] - Starting iteration 283. [2026-03-25 21:49:31,942][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:49:31,943][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:49:38,824][__main__][INFO] - Number of regex retries in iteration 283: 0 [2026-03-25 21:49:38,825][__main__][INFO] - agents played in iteration 283 are Bob, Alice [2026-03-25 21:49:39,777][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:49:40,398][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:49:40,861][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:49:41,374][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:49:41,881][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:49:42,388][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:49:42,896][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:49:43,404][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:49:43,911][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:49:44,419][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:49:44,925][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:49:45,432][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:49:45,939][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:49:46,446][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:49:46,953][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:49:47,459][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:49:47,965][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:49:48,472][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:49:48,982][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:49:49,491][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:49:50,000][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:49:50,509][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:49:51,019][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:49:51,527][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:49:52,035][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:49:52,544][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:49:53,051][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:49:53,560][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:49:54,067][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:49:54,574][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:49:55,082][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:49:55,588][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:49:56,095][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:49:56,602][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:49:57,109][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:49:57,615][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:49:58,122][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:49:58,629][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:49:59,137][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:49:59,644][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:50:00,151][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:50:00,660][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:50:01,168][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:50:01,674][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:50:02,181][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:50:02,689][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:50:03,199][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:50:03,706][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:50:04,214][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:50:04,723][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:50:05,231][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:50:05,738][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:50:06,245][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:50:06,753][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:50:07,260][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:50:07,767][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:50:08,274][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:50:08,781][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:50:09,288][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:50:09,797][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:50:10,305][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:50:10,812][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:50:11,321][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:50:11,830][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:50:12,340][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:50:12,849][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:50:13,357][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:50:13,864][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:50:14,371][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:50:14,879][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:50:15,386][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:50:15,892][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:50:16,401][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:50:16,910][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:50:17,416][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:50:17,923][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:50:18,430][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:50:18,938][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:50:19,444][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:50:19,950][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:50:20,455][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:50:20,962][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:50:21,470][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:50:21,978][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:50:22,485][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:50:22,994][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:50:23,502][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:50:24,010][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:50:24,521][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:50:25,030][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:50:25,537][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:50:26,042][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:50:26,548][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:50:27,056][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:50:27,563][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:50:28,071][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:50:28,578][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:50:29,085][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:50:29,591][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:50:30,098][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:50:30,605][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:50:31,111][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:50:31,618][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:50:32,125][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:50:32,631][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:50:33,139][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:50:33,646][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:50:34,154][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:50:34,662][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:50:35,169][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:50:35,676][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:50:36,183][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:50:36,689][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:50:37,199][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:50:37,705][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:50:38,212][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:50:38,720][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:50:39,227][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:50:39,734][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:50:40,240][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:50:40,747][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:50:41,255][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:50:41,762][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:50:42,270][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:50:42,777][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:50:43,285][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:50:43,793][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:50:44,301][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:50:44,808][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:50:45,317][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21736 tokens. [2026-03-25 21:50:45,978][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 21:50:46,729][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:50:46,732][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:50:46,733][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:50:47,565][__main__][INFO] - Iteration 284 took 1m 15s (9.10% Gen, 89.80% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 45m 35s. Estimated total time: 63h 1m 9s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 2s, 500 more iterations: 10h 30m 11s. [2026-03-25 21:50:47,567][__main__][INFO] - Starting iteration 284. [2026-03-25 21:50:47,970][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:50:47,970][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:50:55,110][__main__][INFO] - Number of regex retries in iteration 284: 0 [2026-03-25 21:50:55,110][__main__][INFO] - agents played in iteration 284 are Bob, Alice [2026-03-25 21:50:56,069][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:50:56,697][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:50:57,161][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:50:57,674][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:50:58,181][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:50:58,688][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:50:59,195][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:50:59,703][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:51:00,210][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:51:00,720][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:51:01,227][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:51:01,734][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:51:02,240][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:51:02,746][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:51:03,253][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:51:03,760][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:51:04,267][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:51:04,774][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:51:05,284][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:51:05,792][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:51:06,300][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:51:06,808][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:51:07,318][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:51:07,825][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:51:08,335][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:51:08,843][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:51:09,354][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:51:09,865][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:51:10,375][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:51:10,884][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:51:11,394][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:51:11,903][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:51:12,412][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:51:12,920][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:51:13,430][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:51:13,940][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:51:14,449][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:51:14,957][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:51:15,466][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:51:15,974][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:51:16,483][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:51:16,992][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:51:17,501][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:51:18,009][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:51:18,518][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:51:19,027][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:51:19,535][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:51:20,044][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:51:20,553][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:51:21,062][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:51:21,569][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:51:22,078][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:51:22,585][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:51:23,092][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:51:23,602][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:51:24,111][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:51:24,620][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:51:25,128][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:51:25,638][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:51:26,146][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:51:26,654][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:51:27,162][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:51:27,670][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:51:28,178][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:51:28,685][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:51:29,193][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:51:29,701][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:51:30,209][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:51:30,717][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:51:31,226][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:51:31,733][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:51:32,241][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:51:32,747][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:51:33,255][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:51:33,763][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:51:34,270][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:51:34,776][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:51:35,284][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:51:35,791][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:51:36,298][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:51:36,805][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:51:37,312][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:51:37,821][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:51:38,329][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:51:38,837][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:51:39,346][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:51:39,855][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:51:40,363][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:51:40,873][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:51:41,381][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:51:41,891][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:51:42,400][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:51:42,909][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:51:43,419][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:51:43,931][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:51:44,440][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:51:44,949][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:51:45,460][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:51:45,968][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:51:46,476][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:51:46,984][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:51:47,494][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:51:48,003][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:51:48,510][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:51:49,020][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:51:49,528][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:51:50,036][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:51:50,545][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:51:51,054][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:51:51,562][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:51:52,071][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:51:52,582][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:51:53,090][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:51:53,599][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:51:54,106][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:51:54,614][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:51:55,123][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:51:55,631][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:51:56,139][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:51:56,646][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:51:57,154][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:51:57,661][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:51:58,169][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:51:58,679][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:51:59,188][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:51:59,697][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:52:00,206][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:52:00,713][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:52:01,221][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:52:01,730][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 21:52:02,406][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 21:52:03,173][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:52:03,176][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:52:03,177][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:52:03,923][__main__][INFO] - Iteration 285 took 1m 15s (9.40% Gen, 89.62% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 57h 0m 52s. Estimated total time: 63h 17m 43s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 35s, 500 more iterations: 10h 32m 57s. [2026-03-25 21:52:03,926][__main__][INFO] - Starting iteration 285. [2026-03-25 21:52:04,326][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:52:04,327][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:52:11,169][__main__][INFO] - Number of regex retries in iteration 285: 0 [2026-03-25 21:52:11,169][__main__][INFO] - agents played in iteration 285 are Bob, Alice [2026-03-25 21:52:12,129][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:52:12,758][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:52:13,223][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:52:13,735][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:52:14,243][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:52:14,750][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:52:15,260][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:52:15,768][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:52:16,274][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:52:16,781][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:52:17,288][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:52:17,795][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:52:18,301][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:52:18,809][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:52:19,316][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:52:19,823][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:52:20,330][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:52:20,837][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:52:21,347][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:52:21,855][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:52:22,363][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:52:22,873][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:52:23,382][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:52:23,891][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:52:24,399][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:52:24,907][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:52:25,415][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:52:25,922][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:52:26,429][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:52:26,937][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:52:27,444][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:52:27,951][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:52:28,457][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:52:28,964][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:52:29,472][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:52:29,981][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:52:30,490][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:52:30,999][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:52:31,507][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:52:32,015][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:52:32,523][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:52:33,031][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:52:33,540][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:52:34,048][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:52:34,556][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:52:35,064][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:52:35,571][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:52:36,079][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:52:36,586][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:52:37,091][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:52:37,597][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:52:38,104][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:52:38,610][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:52:39,115][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:52:39,623][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:52:40,131][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:52:40,636][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:52:41,141][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:52:41,650][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:52:42,159][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:52:42,668][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:52:43,175][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:52:43,684][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:52:44,193][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:52:44,701][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:52:45,209][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:52:45,717][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:52:46,221][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:52:46,729][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:52:47,236][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:52:47,743][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:52:48,251][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:52:48,757][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:52:49,265][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:52:49,771][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:52:50,278][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:52:50,784][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:52:51,290][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:52:51,799][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:52:52,306][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:52:52,812][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:52:53,320][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:52:53,830][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:52:54,339][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:52:54,847][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:52:55,354][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:52:55,862][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:52:56,370][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:52:56,877][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:52:57,385][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:52:57,892][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:52:58,400][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:52:58,909][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:52:59,418][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:52:59,926][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:53:00,435][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:53:00,942][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:53:01,450][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:53:01,959][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:53:02,468][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:53:02,977][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:53:03,485][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:53:03,994][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:53:04,503][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:53:05,012][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:53:05,522][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:53:06,031][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:53:06,539][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:53:07,047][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:53:07,556][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:53:08,064][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:53:08,571][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:53:09,078][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:53:09,587][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:53:10,094][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:53:10,601][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:53:11,108][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:53:11,615][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:53:12,122][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:53:12,629][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:53:13,135][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:53:13,643][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:53:14,153][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:53:14,661][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:53:15,170][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:53:15,680][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:53:16,189][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:53:16,698][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:53:17,206][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:53:17,715][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21744 tokens. [2026-03-25 21:53:18,377][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-25 21:53:19,144][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:53:19,147][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:53:19,148][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:53:19,825][__main__][INFO] - Iteration 286 took 1m 15s (9.06% Gen, 90.04% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 36m 51s. Estimated total time: 62h 54m 58s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 49s, 500 more iterations: 10h 29m 9s. [2026-03-25 21:53:19,827][__main__][INFO] - Starting iteration 286. [2026-03-25 21:53:20,228][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:53:20,228][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:53:24,750][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:53:27,058][__main__][INFO] - Number of regex retries in iteration 286: 1 [2026-03-25 21:53:27,059][__main__][INFO] - agents played in iteration 286 are Bob, Alice [2026-03-25 21:53:28,008][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:53:28,640][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:53:29,104][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:53:29,618][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:53:30,127][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:53:30,635][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:53:31,143][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:53:31,652][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:53:32,160][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:53:32,668][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:53:33,174][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:53:33,679][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:53:34,183][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:53:34,688][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:53:35,192][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:53:35,698][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:53:36,204][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:53:36,709][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:53:37,222][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:53:37,732][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:53:38,241][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:53:38,750][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:53:39,261][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:53:39,770][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:53:40,278][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:53:40,787][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:53:41,294][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:53:41,803][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:53:42,312][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:53:42,822][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:53:43,333][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:53:43,842][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:53:44,350][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:53:44,861][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:53:45,369][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:53:45,875][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:53:46,383][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:53:46,890][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:53:47,398][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:53:47,904][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:53:48,410][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:53:48,918][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:53:49,426][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:53:49,933][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:53:50,439][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:53:50,946][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:53:51,453][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:53:51,960][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:53:52,467][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:53:52,973][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:53:53,482][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:53:53,990][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:53:54,499][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:53:55,009][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:53:55,518][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:53:56,027][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:53:56,536][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:53:57,045][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:53:57,551][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:53:58,058][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:53:58,565][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:53:59,071][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:53:59,578][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:54:00,086][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:54:00,591][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:54:01,100][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:54:01,609][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:54:02,115][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:54:02,623][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:54:03,131][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:54:03,639][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:54:04,146][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:54:04,652][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:54:05,161][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:54:05,666][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:54:06,169][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:54:06,673][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:54:07,179][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:54:07,683][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:54:08,187][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:54:08,690][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:54:09,194][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:54:09,702][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:54:10,210][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:54:10,719][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:54:11,228][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:54:11,739][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:54:12,248][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:54:12,757][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:54:13,266][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:54:13,774][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:54:14,283][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:54:14,791][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:54:15,300][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:54:15,807][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:54:16,315][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:54:16,824][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:54:17,332][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:54:17,839][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:54:18,347][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:54:18,854][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:54:19,362][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:54:19,870][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:54:20,378][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:54:20,885][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:54:21,392][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:54:21,900][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:54:22,409][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:54:22,917][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:54:23,424][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:54:23,932][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:54:24,441][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:54:24,949][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:54:25,457][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:54:25,967][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:54:26,476][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:54:26,984][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:54:27,492][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:54:28,002][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:54:28,511][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:54:29,021][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:54:29,531][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:54:30,038][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:54:30,545][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:54:31,052][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:54:31,561][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:54:32,067][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:54:32,575][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:54:33,082][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:54:33,589][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 21:54:34,254][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.15%, Current % of VRAM taken: 60.51%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 21:54:35,014][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:54:35,016][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:54:35,018][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:54:35,709][__main__][INFO] - Iteration 287 took 1m 15s (9.05% Gen, 90.03% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 34m 43s. Estimated total time: 62h 54m 5s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 48s, 500 more iterations: 10h 29m 0s. [2026-03-25 21:54:35,711][__main__][INFO] - Starting iteration 287. [2026-03-25 21:54:36,114][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:54:36,114][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:54:38,457][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:54:43,029][__main__][INFO] - Number of regex retries in iteration 287: 1 [2026-03-25 21:54:43,030][__main__][INFO] - agents played in iteration 287 are Bob, Alice [2026-03-25 21:54:43,984][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:54:44,621][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:54:45,085][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:54:45,599][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:54:46,108][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:54:46,618][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:54:47,126][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:54:47,635][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:54:48,143][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:54:48,652][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:54:49,160][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:54:49,668][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:54:50,179][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:54:50,688][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:54:51,196][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:54:51,705][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:54:52,214][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:54:52,723][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:54:53,234][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:54:53,743][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:54:54,253][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:54:54,762][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:54:55,271][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:54:55,781][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:54:56,291][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:54:56,802][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:54:57,311][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:54:57,820][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:54:58,329][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:54:58,837][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:54:59,345][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:54:59,854][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:55:00,362][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:55:00,870][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:55:01,380][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:55:01,889][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:55:02,399][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:55:02,908][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:55:03,419][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:55:03,929][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:55:04,438][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:55:04,948][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:55:05,457][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:55:05,965][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:55:06,472][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:55:06,981][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:55:07,489][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:55:07,997][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:55:08,505][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:55:09,014][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:55:09,521][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:55:10,029][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:55:10,538][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:55:11,046][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:55:11,554][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:55:12,062][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:55:12,569][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:55:13,079][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:55:13,587][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:55:14,096][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:55:14,606][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:55:15,115][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:55:15,624][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:55:16,133][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:55:16,641][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:55:17,151][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:55:17,659][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:55:18,167][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:55:18,675][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:55:19,184][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:55:19,692][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:55:20,202][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:55:20,711][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:55:21,221][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:55:21,730][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:55:22,239][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:55:22,748][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:55:23,257][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:55:23,765][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:55:24,273][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:55:24,780][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:55:25,289][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:55:25,801][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:55:26,311][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:55:26,821][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:55:27,331][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:55:27,842][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:55:28,352][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:55:28,862][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:55:29,372][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:55:29,881][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:55:30,390][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:55:30,899][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:55:31,408][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:55:31,917][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:55:32,427][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:55:32,936][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:55:33,446][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:55:33,956][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:55:34,466][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:55:34,976][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:55:35,486][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:55:35,996][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:55:36,505][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:55:37,016][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:55:37,525][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:55:38,034][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:55:38,543][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:55:39,052][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:55:39,560][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:55:40,069][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:55:40,579][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:55:41,088][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:55:41,596][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:55:42,105][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:55:42,612][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:55:43,121][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:55:43,629][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:55:44,138][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:55:44,646][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:55:45,154][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:55:45,662][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:55:46,171][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:55:46,681][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:55:47,190][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:55:47,700][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:55:48,209][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:55:48,719][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:55:49,228][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:55:49,740][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 21:55:50,408][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 21:55:51,173][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:55:51,175][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:55:51,177][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:55:51,910][__main__][INFO] - Iteration 288 took 1m 15s (9.12% Gen, 89.91% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 49m 12s. Estimated total time: 63h 9m 51s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 19s, 500 more iterations: 10h 31m 38s. [2026-03-25 21:55:51,912][__main__][INFO] - Starting iteration 288. [2026-03-25 21:55:52,313][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:55:52,313][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:55:52,935][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:55:58,757][__main__][INFO] - Number of regex retries in iteration 288: 1 [2026-03-25 21:55:58,758][__main__][INFO] - agents played in iteration 288 are Bob, Alice [2026-03-25 21:55:59,721][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:56:00,361][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:56:00,824][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:56:01,336][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:56:01,842][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:56:02,349][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:56:02,857][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:56:03,363][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:56:03,870][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:56:04,377][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:56:04,888][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:56:05,395][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:56:05,903][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:56:06,411][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:56:06,919][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:56:07,428][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:56:07,936][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:56:08,445][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:56:08,955][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:56:09,462][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:56:09,970][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:56:10,478][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:56:10,984][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:56:11,491][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:56:12,000][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:56:12,510][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:56:13,038][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:56:13,550][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:56:14,059][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:56:14,566][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:56:15,075][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:56:15,583][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:56:16,092][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:56:16,601][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:56:17,110][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:56:17,619][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:56:18,127][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:56:18,634][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:56:19,142][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:56:19,650][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:56:20,157][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:56:20,666][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:56:21,173][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:56:21,682][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:56:22,188][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:56:22,698][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:56:23,205][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:56:23,714][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:56:24,223][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:56:24,730][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:56:25,238][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:56:25,747][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:56:26,254][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:56:26,762][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:56:27,270][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:56:27,777][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:56:28,283][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:56:28,792][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:56:29,299][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:56:29,807][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:56:30,314][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:56:30,823][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:56:31,331][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:56:31,840][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:56:32,348][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:56:32,856][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:56:33,362][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:56:33,869][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:56:34,375][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:56:34,882][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:56:35,388][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:56:35,895][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:56:36,402][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:56:36,909][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:56:37,419][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:56:37,927][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:56:38,435][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:56:38,943][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:56:39,451][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:56:39,959][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:56:40,465][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:56:40,974][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:56:41,482][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:56:41,989][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:56:42,496][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:56:43,005][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:56:43,512][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:56:44,020][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:56:44,528][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:56:45,035][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:56:45,544][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:56:46,052][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:56:46,562][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:56:47,071][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:56:47,579][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:56:48,087][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:56:48,595][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:56:49,104][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:56:49,612][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:56:50,122][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:56:50,629][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:56:51,139][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:56:51,646][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:56:52,155][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:56:52,662][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:56:53,172][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:56:53,679][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:56:54,188][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:56:54,694][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:56:55,204][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:56:55,711][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:56:56,222][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:56:56,730][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:56:57,240][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:56:57,747][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:56:58,255][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:56:58,762][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:56:59,272][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:56:59,778][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:57:00,288][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:57:00,794][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:57:01,303][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:57:01,810][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:57:02,320][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:57:02,829][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:57:03,338][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:57:03,846][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:57:04,354][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:57:04,862][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:57:05,370][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 21:57:06,030][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-25 21:57:06,784][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:57:06,786][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:57:06,788][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:57:07,453][__main__][INFO] - Iteration 289 took 1m 15s (8.58% Gen, 90.54% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 15m 8s. Estimated total time: 62h 37m 2s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 14s, 500 more iterations: 10h 26m 10s. [2026-03-25 21:57:07,455][__main__][INFO] - Starting iteration 289. [2026-03-25 21:57:07,856][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:57:07,857][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:57:08,496][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:57:08,501][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:57:08,504][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:57:12,284][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:57:14,161][__main__][INFO] - Number of regex retries in iteration 289: 4 [2026-03-25 21:57:14,162][__main__][INFO] - agents played in iteration 289 are Bob, Alice [2026-03-25 21:57:15,128][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:57:15,764][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:57:16,228][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:57:16,741][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:57:17,249][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:57:17,757][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:57:18,265][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:57:18,773][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:57:19,281][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:57:19,789][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:57:20,300][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:57:20,809][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:57:21,317][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:57:21,826][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:57:22,333][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:57:22,842][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:57:23,351][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:57:23,859][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:57:24,369][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:57:24,880][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:57:25,389][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:57:25,898][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:57:26,406][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:57:26,915][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:57:27,424][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:57:27,933][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:57:28,443][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:57:28,952][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:57:29,461][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:57:29,970][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:57:30,479][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:57:30,988][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:57:31,495][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:57:32,004][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:57:32,511][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:57:33,019][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:57:33,526][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:57:34,033][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:57:34,541][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:57:35,049][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:57:35,556][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:57:36,063][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:57:36,590][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:57:37,104][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:57:37,613][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:57:38,122][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:57:38,632][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:57:39,142][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:57:39,651][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:57:40,160][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:57:40,668][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:57:41,178][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:57:41,685][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:57:42,193][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:57:42,702][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:57:43,210][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:57:43,720][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:57:44,229][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:57:44,737][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:57:45,245][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:57:45,753][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:57:46,261][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:57:46,769][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:57:47,277][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:57:47,784][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:57:48,292][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:57:48,801][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:57:49,308][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:57:49,816][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:57:50,324][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:57:50,831][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:57:51,339][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:57:51,847][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:57:52,355][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:57:52,862][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:57:53,371][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:57:53,879][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:57:54,388][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:57:54,896][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:57:55,404][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:57:55,913][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:57:56,423][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:57:56,932][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:57:57,441][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:57:57,950][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:57:58,459][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:57:58,967][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:57:59,475][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:57:59,984][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:58:00,493][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:58:01,002][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:58:01,510][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:58:02,019][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:58:02,529][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:58:03,039][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:58:03,548][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:58:04,056][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:58:04,566][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:58:05,073][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:58:05,580][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:58:06,087][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:58:06,594][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:58:07,102][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:58:07,609][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:58:08,117][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:58:08,626][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:58:09,136][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:58:09,644][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:58:10,154][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:58:10,664][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:58:11,172][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:58:11,681][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:58:12,189][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:58:12,699][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:58:13,208][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:58:13,717][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:58:14,227][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:58:14,737][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:58:15,246][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:58:15,754][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:58:16,263][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:58:16,772][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:58:17,279][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:58:17,787][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:58:18,296][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:58:18,804][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:58:19,312][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:58:19,822][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:58:20,331][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:58:20,839][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21740 tokens. [2026-03-25 21:58:21,499][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 21:58:22,258][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:58:22,261][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:58:22,262][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:58:22,972][__main__][INFO] - Iteration 290 took 1m 15s (8.39% Gen, 90.66% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 12m 39s. Estimated total time: 62h 35m 49s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 11s, 500 more iterations: 10h 25m 58s. [2026-03-25 21:58:22,974][__main__][INFO] - Starting iteration 290. [2026-03-25 21:58:23,375][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:58:23,375][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:58:25,755][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:58:30,363][__main__][INFO] - Number of regex retries in iteration 290: 1 [2026-03-25 21:58:30,364][__main__][INFO] - agents played in iteration 290 are Bob, Alice [2026-03-25 21:58:31,341][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:58:31,982][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:58:32,447][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:58:32,960][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:58:33,469][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:58:33,978][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:58:34,486][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:58:34,993][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:58:35,502][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:58:36,012][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:58:36,523][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:58:37,033][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:58:37,542][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:58:38,050][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:58:38,560][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:58:39,070][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:58:39,579][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:58:40,089][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:58:40,597][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:58:41,105][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:58:41,613][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:58:42,122][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:58:42,631][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:58:43,139][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:58:43,647][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 21:58:44,155][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 21:58:44,663][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 21:58:45,170][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 21:58:45,677][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 21:58:46,185][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 21:58:46,691][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 21:58:47,199][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 21:58:47,706][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 21:58:48,213][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 21:58:48,721][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 21:58:49,229][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 21:58:49,737][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 21:58:50,244][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 21:58:50,751][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 21:58:51,259][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 21:58:51,766][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 21:58:52,274][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 21:58:52,782][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 21:58:53,291][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 21:58:53,799][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 21:58:54,308][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 21:58:54,816][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 21:58:55,324][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 21:58:55,833][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 21:58:56,342][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 21:58:56,850][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 21:58:57,360][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 21:58:57,869][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 21:58:58,378][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 21:58:58,887][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 21:58:59,395][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 21:58:59,904][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 21:59:00,413][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 21:59:00,924][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 21:59:01,434][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 21:59:01,943][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 21:59:02,452][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 21:59:02,962][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 21:59:03,471][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 21:59:03,982][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 21:59:04,491][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 21:59:04,999][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 21:59:05,507][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 21:59:06,015][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 21:59:06,524][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 21:59:07,032][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 21:59:07,541][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 21:59:08,049][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 21:59:08,558][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 21:59:09,066][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 21:59:09,575][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 21:59:10,084][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 21:59:10,592][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 21:59:11,101][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 21:59:11,609][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 21:59:12,120][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 21:59:12,629][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 21:59:13,136][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 21:59:13,644][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 21:59:14,151][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 21:59:14,659][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 21:59:15,166][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 21:59:15,674][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 21:59:16,182][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 21:59:16,690][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 21:59:17,197][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 21:59:17,705][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 21:59:18,211][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 21:59:18,719][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 21:59:19,226][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 21:59:19,733][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 21:59:20,241][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 21:59:20,749][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 21:59:21,256][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 21:59:21,762][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 21:59:22,269][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 21:59:22,777][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 21:59:23,284][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 21:59:23,791][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 21:59:24,299][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 21:59:24,806][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 21:59:25,314][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 21:59:25,822][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 21:59:26,332][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 21:59:26,839][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 21:59:27,347][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 21:59:27,855][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 21:59:28,363][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 21:59:28,871][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 21:59:29,379][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 21:59:29,888][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 21:59:30,396][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 21:59:30,905][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 21:59:31,413][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 21:59:31,923][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 21:59:32,433][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 21:59:32,941][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 21:59:33,451][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 21:59:33,961][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 21:59:34,470][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 21:59:34,977][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 21:59:35,484][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 21:59:35,993][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 21:59:36,503][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 21:59:37,013][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 21:59:37,682][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.66%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 21:59:38,434][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 21:59:38,436][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 21:59:38,438][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 21:59:39,097][__main__][INFO] - Iteration 291 took 1m 15s (9.23% Gen, 89.90% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 41m 42s. Estimated total time: 63h 6m 8s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 12s, 500 more iterations: 10h 31m 1s. [2026-03-25 21:59:39,099][__main__][INFO] - Starting iteration 291. [2026-03-25 21:59:39,502][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 21:59:39,503][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 21:59:41,324][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 21:59:46,303][__main__][INFO] - Number of regex retries in iteration 291: 1 [2026-03-25 21:59:46,304][__main__][INFO] - agents played in iteration 291 are Bob, Alice [2026-03-25 21:59:47,263][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 21:59:47,889][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 21:59:48,354][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 21:59:48,867][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 21:59:49,376][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 21:59:49,885][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 21:59:50,393][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 21:59:50,901][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 21:59:51,410][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 21:59:51,918][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 21:59:52,427][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 21:59:52,936][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 21:59:53,445][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 21:59:53,953][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 21:59:54,462][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 21:59:54,972][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 21:59:55,480][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 21:59:55,988][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 21:59:56,497][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 21:59:57,005][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 21:59:57,513][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 21:59:58,021][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 21:59:58,530][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 21:59:59,039][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 21:59:59,547][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:00:00,053][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:00:00,560][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:00:01,068][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:00:01,575][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:00:02,083][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:00:02,590][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:00:03,099][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:00:03,606][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:00:04,113][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:00:04,622][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:00:05,131][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:00:05,639][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:00:06,149][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:00:06,659][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:00:07,169][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:00:07,678][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:00:08,188][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:00:08,696][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:00:09,206][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:00:09,715][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:00:10,224][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:00:10,733][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:00:11,242][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:00:11,750][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:00:12,259][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:00:12,767][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:00:13,275][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:00:13,784][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:00:14,293][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:00:14,801][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:00:15,309][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:00:15,820][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:00:16,329][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:00:16,837][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:00:17,346][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:00:17,854][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:00:18,363][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:00:18,870][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:00:19,380][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:00:19,888][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:00:20,395][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:00:20,905][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:00:21,414][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:00:21,924][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:00:22,433][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:00:22,943][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:00:23,452][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:00:23,962][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:00:24,471][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:00:24,982][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:00:25,492][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:00:26,002][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:00:26,511][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:00:27,022][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:00:27,530][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:00:28,039][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:00:28,549][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:00:29,059][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:00:29,568][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:00:30,075][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:00:30,585][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:00:31,094][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:00:31,603][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:00:32,112][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:00:32,621][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:00:33,129][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:00:33,636][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:00:34,142][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:00:34,649][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:00:35,156][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:00:35,663][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:00:36,170][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:00:36,678][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:00:37,187][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:00:37,696][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:00:38,205][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:00:38,714][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:00:39,223][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:00:39,732][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:00:40,243][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:00:40,753][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:00:41,261][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:00:41,768][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:00:42,276][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:00:42,784][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:00:43,292][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:00:43,801][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:00:44,309][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:00:44,818][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:00:45,326][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:00:45,835][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:00:46,344][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:00:46,852][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:00:47,362][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:00:47,870][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:00:48,379][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:00:48,887][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:00:49,394][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:00:49,903][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:00:50,411][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:00:50,918][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:00:51,426][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:00:51,935][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:00:52,444][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:00:52,952][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 22:00:53,617][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:05 [2026-03-25 22:00:54,375][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:00:54,378][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:00:54,379][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:00:55,052][__main__][INFO] - Iteration 292 took 1m 15s (9.00% Gen, 90.11% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 31m 50s. Estimated total time: 62h 57m 32s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 55s, 500 more iterations: 10h 29m 35s. [2026-03-25 22:00:55,054][__main__][INFO] - Starting iteration 292. [2026-03-25 22:00:55,457][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 22:00:55,457][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:01:01,825][__main__][INFO] - Number of regex retries in iteration 292: 0 [2026-03-25 22:01:02,117][__main__][INFO] - agents played in iteration 292 are Bob, Alice [2026-03-25 22:01:03,077][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:01:03,698][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:01:04,162][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:01:04,674][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:01:05,182][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:01:05,689][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:01:06,197][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:01:06,705][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:01:07,213][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:01:07,722][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:01:08,232][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:01:08,741][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:01:09,248][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:01:09,755][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:01:10,263][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:01:10,770][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:01:11,277][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:01:11,785][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:01:12,291][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:01:12,800][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:01:13,307][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:01:13,813][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:01:14,321][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:01:14,828][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:01:15,336][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:01:15,843][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:01:16,350][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:01:16,859][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:01:17,367][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:01:17,874][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:01:18,383][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:01:18,890][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:01:19,399][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:01:19,906][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:01:20,413][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:01:20,921][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:01:21,428][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:01:21,935][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:01:22,443][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:01:22,951][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:01:23,459][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:01:23,966][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:01:24,475][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:01:24,983][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:01:25,490][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:01:25,998][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:01:26,507][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:01:27,016][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:01:27,525][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:01:28,032][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:01:28,544][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:01:29,053][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:01:29,561][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:01:30,070][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:01:30,579][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:01:31,088][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:01:31,596][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:01:32,104][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:01:32,611][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:01:33,119][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:01:33,627][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:01:34,135][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:01:34,643][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:01:35,150][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:01:35,658][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:01:36,166][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:01:36,672][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:01:37,179][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:01:37,686][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:01:38,191][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:01:38,698][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:01:39,205][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:01:39,711][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:01:40,219][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:01:40,727][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:01:41,236][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:01:41,744][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:01:42,252][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:01:42,761][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:01:43,269][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:01:43,778][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:01:44,287][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:01:44,794][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:01:45,300][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:01:45,806][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:01:46,312][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:01:46,820][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:01:47,327][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:01:47,833][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:01:48,341][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:01:48,849][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:01:49,357][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:01:49,865][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:01:50,372][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:01:50,881][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:01:51,388][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:01:51,895][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:01:52,403][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:01:52,911][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:01:53,419][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:01:53,927][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:01:54,436][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:01:54,943][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:01:55,452][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:01:55,960][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:01:56,468][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:01:56,976][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:01:57,483][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:01:57,990][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:01:58,501][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:01:59,011][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:01:59,518][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:02:00,027][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:02:00,535][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:02:01,044][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:02:01,552][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:02:02,061][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:02:02,570][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:02:03,078][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:02:03,587][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:02:04,096][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:02:04,605][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:02:05,112][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:02:05,621][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:02:06,129][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:02:06,638][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:02:07,146][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:02:07,654][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:02:08,163][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:02:08,671][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 22:02:09,335][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 22:02:10,085][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:02:10,087][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:02:10,089][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:02:10,756][__main__][INFO] - Iteration 293 took 1m 15s (8.84% Gen, 90.27% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 18m 3s. Estimated total time: 62h 45m 0s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 30s, 500 more iterations: 10h 27m 30s. [2026-03-25 22:02:10,758][__main__][INFO] - Starting iteration 293. [2026-03-25 22:02:11,165][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 22:02:11,165][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:02:17,864][__main__][INFO] - Number of regex retries in iteration 293: 0 [2026-03-25 22:02:18,161][__main__][INFO] - agents played in iteration 293 are Bob, Alice [2026-03-25 22:02:19,119][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:02:19,747][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:02:20,212][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:02:20,725][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:02:21,233][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:02:21,742][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:02:22,251][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:02:22,758][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:02:23,266][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:02:23,774][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:02:24,281][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:02:24,789][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:02:25,296][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:02:25,805][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:02:26,313][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:02:26,821][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:02:27,329][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:02:27,838][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:02:28,347][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:02:28,855][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:02:29,363][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:02:29,871][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:02:30,379][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:02:30,886][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:02:31,393][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:02:31,902][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:02:32,410][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:02:32,918][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:02:33,425][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:02:33,934][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:02:34,441][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:02:34,950][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:02:35,457][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:02:35,964][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:02:36,472][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:02:36,979][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:02:37,486][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:02:37,993][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:02:38,501][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:02:39,008][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:02:39,516][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:02:40,023][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:02:40,534][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:02:41,042][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:02:41,549][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:02:42,058][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:02:42,566][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:02:43,074][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:02:43,583][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:02:44,092][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:02:44,599][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:02:45,106][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:02:45,613][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:02:46,121][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:02:46,629][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:02:47,135][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:02:47,644][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:02:48,152][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:02:48,658][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:02:49,166][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:02:49,672][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:02:50,181][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:02:50,688][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:02:51,194][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:02:51,703][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:02:52,210][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:02:52,718][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:02:53,226][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:02:53,735][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:02:54,243][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:02:54,751][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:02:55,258][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:02:55,766][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:02:56,274][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:02:56,782][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:02:57,289][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:02:57,797][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:02:58,304][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:02:58,812][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:02:59,321][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:02:59,830][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:03:00,339][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:03:00,847][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:03:01,354][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:03:01,862][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:03:02,370][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:03:02,877][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:03:03,385][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:03:03,893][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:03:04,400][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:03:04,907][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:03:05,415][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:03:05,922][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:03:06,430][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:03:06,937][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:03:07,445][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:03:07,952][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:03:08,459][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:03:08,965][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:03:09,472][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:03:09,979][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:03:10,486][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:03:10,993][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:03:11,500][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:03:12,008][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:03:12,515][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:03:13,024][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:03:13,532][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:03:14,041][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:03:14,549][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:03:15,058][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:03:15,565][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:03:16,073][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:03:16,581][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:03:17,088][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:03:17,595][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:03:18,102][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:03:18,609][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:03:19,116][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:03:19,622][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:03:20,131][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:03:20,638][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:03:21,143][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:03:21,649][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:03:22,155][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:03:22,661][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:03:23,167][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:03:23,673][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:03:24,180][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:03:24,685][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 22:03:25,336][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 22:03:26,087][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:03:26,089][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:03:26,091][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:03:26,761][__main__][INFO] - Iteration 294 took 1m 15s (9.25% Gen, 89.86% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 56h 31m 38s. Estimated total time: 62h 59m 52s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 59s, 500 more iterations: 10h 29m 58s. [2026-03-25 22:03:26,764][__main__][INFO] - Starting iteration 294. [2026-03-25 22:03:27,167][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 22:03:27,168][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:03:27,806][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:03:34,206][__main__][INFO] - Number of regex retries in iteration 294: 1 [2026-03-25 22:03:34,206][__main__][INFO] - agents played in iteration 294 are Bob, Alice [2026-03-25 22:03:35,165][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:03:35,821][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:03:36,285][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:03:36,799][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:03:37,307][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:03:37,815][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:03:38,324][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:03:38,833][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:03:39,341][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:03:39,850][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:03:40,360][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:03:40,868][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:03:41,375][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:03:41,881][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:03:42,388][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:03:42,895][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:03:43,403][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:03:43,909][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:03:44,421][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:03:44,930][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:03:45,437][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:03:45,945][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:03:46,452][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:03:46,961][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:03:47,468][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:03:47,976][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:03:48,483][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:03:48,990][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:03:49,498][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:03:50,006][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:03:50,513][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:03:51,020][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:03:51,528][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:03:52,035][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:03:52,546][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:03:53,057][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:03:53,565][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:03:54,074][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:03:54,582][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:03:55,091][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:03:55,600][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:03:56,109][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:03:56,617][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:03:57,126][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:03:57,634][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:03:58,142][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:03:58,650][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:03:59,159][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:03:59,667][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:04:00,175][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:04:00,680][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:04:01,186][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:04:01,691][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:04:02,196][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:04:02,702][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:04:03,208][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:04:03,713][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:04:04,220][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:04:04,729][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:04:05,237][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:04:05,744][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:04:06,251][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:04:06,759][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:04:07,265][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:04:07,771][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:04:08,280][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:04:08,787][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:04:09,294][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:04:09,803][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:04:10,310][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:04:10,818][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:04:11,326][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:04:11,834][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:04:12,341][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:04:12,849][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:04:13,356][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:04:13,863][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:04:14,371][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:04:14,877][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:04:15,384][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:04:15,890][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:04:16,397][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:04:16,905][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:04:17,413][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:04:17,921][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:04:18,429][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:04:18,936][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:04:19,445][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:04:19,951][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:04:20,458][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:04:20,965][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:04:21,471][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:04:21,977][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:04:22,485][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:04:22,991][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:04:23,498][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:04:24,005][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:04:24,512][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:04:25,022][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:04:25,530][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:04:26,039][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:04:26,547][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:04:27,056][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:04:27,564][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:04:28,072][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:04:28,583][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:04:29,090][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:04:29,595][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:04:30,102][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:04:30,611][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:04:31,120][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:04:31,629][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:04:32,136][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:04:32,645][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:04:33,150][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:04:33,655][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:04:34,160][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:04:34,665][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:04:35,170][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:04:35,675][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:04:36,180][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:04:36,687][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:04:37,195][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:04:37,704][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:04:38,212][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:04:38,720][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:04:39,227][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:04:39,735][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:04:40,243][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:04:40,750][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21737 tokens. [2026-03-25 22:04:41,429][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 22:04:42,195][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:04:42,198][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:04:42,199][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:04:42,891][__main__][INFO] - Iteration 295 took 1m 15s (9.30% Gen, 89.79% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 56h 36m 43s. Estimated total time: 63h 6m 12s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 12s, 500 more iterations: 10h 31m 2s. [2026-03-25 22:04:42,893][__main__][INFO] - Starting iteration 295. [2026-03-25 22:04:43,297][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 22:04:43,297][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:04:49,893][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:04:50,261][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:04:51,397][__main__][INFO] - Number of regex retries in iteration 295: 2 [2026-03-25 22:04:51,398][__main__][INFO] - agents played in iteration 295 are Bob, Alice [2026-03-25 22:04:52,379][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:04:53,007][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:04:53,472][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:04:53,985][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:04:54,493][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:04:55,001][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:04:55,509][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:04:56,021][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:04:56,531][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:04:57,039][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:04:57,548][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:04:58,056][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:04:58,565][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:04:59,075][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:04:59,582][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:05:00,091][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:05:00,599][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:05:01,106][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:05:01,614][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:05:02,123][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:05:02,633][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:05:03,141][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:05:03,649][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:05:04,158][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:05:04,667][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:05:05,175][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:05:05,684][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:05:06,193][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:05:06,701][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:05:07,209][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:05:07,717][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:05:08,225][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:05:08,733][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:05:09,242][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:05:09,749][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:05:10,258][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:05:10,767][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:05:11,274][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:05:11,783][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:05:12,290][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:05:12,798][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:05:13,306][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:05:13,814][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:05:14,322][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:05:14,830][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:05:15,339][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:05:15,847][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:05:16,356][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:05:16,864][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:05:17,372][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:05:17,880][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:05:18,389][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:05:18,897][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:05:19,405][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:05:19,912][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:05:20,420][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:05:20,928][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:05:21,436][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:05:21,944][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:05:22,451][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:05:22,957][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:05:23,464][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:05:23,972][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:05:24,479][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:05:24,985][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:05:25,491][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:05:26,001][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:05:26,509][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:05:27,017][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:05:27,526][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:05:28,035][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:05:28,544][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:05:29,052][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:05:29,562][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:05:30,070][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:05:30,576][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:05:31,084][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:05:31,591][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:05:32,100][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:05:32,609][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:05:33,117][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:05:33,625][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:05:34,134][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:05:34,642][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:05:35,151][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:05:35,660][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:05:36,167][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:05:36,674][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:05:37,183][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:05:37,691][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:05:38,199][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:05:38,707][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:05:39,216][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:05:39,724][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:05:40,233][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:05:40,742][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:05:41,250][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:05:41,758][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:05:42,266][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:05:42,773][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:05:43,282][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:05:43,790][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:05:44,298][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:05:44,806][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:05:45,314][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:05:45,823][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:05:46,340][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:05:46,849][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:05:47,359][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:05:47,868][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:05:48,377][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:05:48,886][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:05:49,396][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:05:49,905][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:05:50,414][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:05:50,923][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:05:51,433][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:05:51,942][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:05:52,451][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:05:52,960][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:05:53,468][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:05:53,977][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:05:54,484][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:05:54,991][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:05:55,499][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:05:56,007][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:05:56,515][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:05:57,022][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:05:57,530][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:05:58,038][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21741 tokens. [2026-03-25 22:05:58,720][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-25 22:05:59,487][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:05:59,490][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:05:59,491][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:06:00,228][__main__][INFO] - Iteration 296 took 1m 16s (10.53% Gen, 88.51% Train). Generation: 8s, Training: 1m 8s. Estimated remaining time: 57h 35m 47s. Estimated total time: 64h 6m 34s. Time estimates for 10 more iterations: 12m 49s, 100 more iterations: 2h 8m 13s, 500 more iterations: 10h 41m 5s. [2026-03-25 22:06:00,230][__main__][INFO] - Starting iteration 296. [2026-03-25 22:06:00,632][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 22:06:00,633][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:06:07,349][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:06:08,130][__main__][INFO] - Number of regex retries in iteration 296: 1 [2026-03-25 22:06:08,131][__main__][INFO] - agents played in iteration 296 are Bob, Alice [2026-03-25 22:06:09,089][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:06:10,009][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:06:10,474][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:06:10,987][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:06:11,496][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:06:12,004][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:06:12,512][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:06:13,022][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:06:13,531][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:06:14,038][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:06:14,548][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:06:15,057][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:06:15,566][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:06:16,076][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:06:16,585][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:06:17,093][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:06:17,601][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:06:18,110][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:06:18,619][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:06:19,128][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:06:19,636][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:06:20,145][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:06:20,653][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:06:21,162][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:06:21,678][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:06:22,188][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:06:22,702][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:06:23,211][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:06:23,722][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:06:24,231][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:06:24,740][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:06:25,249][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:06:25,757][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:06:26,266][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:06:26,778][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:06:27,288][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:06:27,799][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:06:28,308][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:06:28,821][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:06:29,331][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:06:29,842][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:06:30,353][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:06:30,861][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:06:31,369][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:06:31,877][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:06:32,386][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:06:32,893][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:06:33,401][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:06:33,909][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:06:34,417][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:06:34,925][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:06:35,433][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:06:35,940][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:06:36,448][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:06:36,955][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:06:37,463][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:06:37,971][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:06:38,478][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:06:38,986][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:06:39,492][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:06:39,999][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:06:40,505][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:06:41,012][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:06:41,520][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:06:42,027][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:06:42,534][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:06:43,042][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:06:43,551][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:06:44,059][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:06:44,567][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:06:45,070][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:06:45,578][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:06:46,086][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:06:46,595][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:06:47,102][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:06:47,610][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:06:48,118][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:06:48,626][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:06:49,135][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:06:49,643][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:06:50,151][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:06:50,659][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:06:51,167][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:06:51,675][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:06:52,183][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:06:52,690][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:06:53,200][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:06:53,708][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:06:54,215][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:06:54,723][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:06:55,232][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:06:55,741][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:06:56,249][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:06:56,756][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:06:57,266][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:06:57,776][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:06:58,286][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:06:58,793][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:06:59,303][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:06:59,813][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:07:00,324][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:07:00,834][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:07:01,344][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:07:01,856][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:07:02,365][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:07:02,876][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:07:03,384][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:07:03,892][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:07:04,402][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:07:04,911][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:07:05,419][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:07:05,928][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:07:06,435][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:07:06,945][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:07:07,453][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:07:07,960][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:07:08,469][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:07:08,976][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:07:09,484][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:07:09,993][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:07:10,501][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:07:11,010][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:07:11,518][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:07:12,025][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:07:12,531][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:07:13,039][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:07:13,546][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:07:14,052][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:07:14,560][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:07:15,067][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21700 tokens. [2026-03-25 22:07:15,743][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 22:07:16,498][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:07:16,501][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:07:16,502][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:07:17,243][__main__][INFO] - Iteration 297 took 1m 16s (9.79% Gen, 89.24% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 57h 18m 31s. Estimated total time: 63h 50m 35s. Time estimates for 10 more iterations: 12m 46s, 100 more iterations: 2h 7m 41s, 500 more iterations: 10h 38m 25s. [2026-03-25 22:07:17,245][__main__][INFO] - Starting iteration 297. [2026-03-25 22:07:17,646][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 22:07:17,647][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:07:24,092][__main__][INFO] - Number of regex retries in iteration 297: 0 [2026-03-25 22:07:24,093][__main__][INFO] - agents played in iteration 297 are Bob, Alice [2026-03-25 22:07:25,077][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:07:25,711][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:07:26,194][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:07:26,708][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:07:27,218][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:07:27,728][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:07:28,236][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:07:28,745][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:07:29,253][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:07:29,762][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:07:30,270][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:07:30,777][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:07:31,284][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:07:31,792][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:07:32,299][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:07:32,805][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:07:33,313][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:07:33,822][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:07:34,329][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:07:34,836][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:07:35,344][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:07:35,851][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:07:36,357][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:07:36,863][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:07:37,370][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:07:37,878][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:07:38,385][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:07:38,893][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:07:39,402][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:07:39,911][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:07:40,419][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:07:40,928][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:07:41,436][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:07:41,945][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:07:42,452][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:07:42,959][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:07:43,465][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:07:43,973][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:07:44,480][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:07:44,986][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:07:45,493][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:07:46,001][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:07:46,510][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:07:47,018][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:07:47,526][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:07:48,035][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:07:48,542][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:07:49,051][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:07:49,560][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:07:50,068][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:07:50,576][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:07:51,084][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:07:51,593][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:07:52,101][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:07:52,610][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:07:53,120][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:07:53,630][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:07:54,139][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:07:54,646][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:07:55,154][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:07:55,662][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:07:56,170][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:07:56,678][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:07:57,186][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:07:57,694][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:07:58,203][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:07:58,710][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:07:59,220][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:07:59,729][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:08:00,238][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:08:00,746][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:08:01,255][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:08:01,764][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:08:02,272][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:08:02,781][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:08:03,289][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:08:03,795][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:08:04,302][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:08:04,809][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:08:05,316][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:08:05,822][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:08:06,329][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:08:06,836][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:08:07,343][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:08:07,851][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:08:08,357][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:08:08,863][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:08:09,370][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:08:09,876][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:08:10,383][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:08:10,891][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:08:11,401][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:08:11,918][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:08:12,428][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:08:12,937][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:08:13,447][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:08:13,956][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:08:14,465][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:08:14,973][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:08:15,480][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:08:15,988][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:08:16,501][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:08:17,011][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:08:17,518][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:08:18,026][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:08:18,534][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:08:19,043][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:08:19,551][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:08:20,058][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:08:20,567][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:08:21,075][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:08:21,583][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:08:22,091][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:08:22,600][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:08:23,109][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:08:23,618][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:08:24,126][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:08:24,635][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:08:25,144][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:08:25,653][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:08:26,162][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:08:26,672][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:08:27,180][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:08:27,688][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:08:28,196][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:08:28,704][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:08:29,212][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:08:29,722][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:08:30,230][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:08:30,740][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 22:08:31,398][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-25 22:08:32,151][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:08:32,154][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:08:32,155][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:08:32,893][__main__][INFO] - Iteration 298 took 1m 15s (8.57% Gen, 90.45% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 9m 1s. Estimated total time: 62h 42m 21s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 24s, 500 more iterations: 10h 27m 3s. [2026-03-25 22:08:32,895][__main__][INFO] - Starting iteration 298. [2026-03-25 22:08:33,296][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 22:08:33,296][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:08:39,925][__main__][INFO] - Number of regex retries in iteration 298: 0 [2026-03-25 22:08:39,926][__main__][INFO] - agents played in iteration 298 are Bob, Alice [2026-03-25 22:08:40,911][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:08:41,542][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:08:42,008][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:08:42,522][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:08:43,031][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:08:43,541][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:08:44,051][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:08:44,558][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:08:45,066][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:08:45,573][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:08:46,078][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:08:46,587][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:08:47,096][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:08:47,604][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:08:48,112][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:08:48,623][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:08:49,131][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:08:49,640][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:08:50,147][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:08:50,654][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:08:51,162][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:08:51,669][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:08:52,177][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:08:52,684][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:08:53,192][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:08:53,699][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:08:54,207][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:08:54,715][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:08:55,223][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:08:55,730][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:08:56,238][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:08:56,746][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:08:57,253][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:08:57,760][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:08:58,271][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:08:58,781][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:08:59,290][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:08:59,798][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:09:00,306][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:09:00,814][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:09:01,323][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:09:01,832][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:09:02,340][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:09:02,847][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:09:03,354][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:09:03,861][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:09:04,368][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:09:04,874][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:09:05,381][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:09:05,888][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:09:06,395][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:09:06,903][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:09:07,411][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:09:07,918][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:09:08,425][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:09:08,932][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:09:09,440][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:09:09,947][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:09:10,453][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:09:10,959][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:09:11,465][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:09:11,969][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:09:12,476][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:09:12,983][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:09:13,490][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:09:13,998][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:09:14,507][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:09:15,015][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:09:15,523][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:09:16,030][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:09:16,538][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:09:17,047][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:09:17,557][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:09:18,065][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:09:18,572][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:09:19,080][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:09:19,589][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:09:20,097][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:09:20,605][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:09:21,112][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:09:21,622][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:09:22,129][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:09:22,638][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:09:23,146][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:09:23,653][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:09:24,161][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:09:24,669][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:09:25,176][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:09:25,684][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:09:26,192][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:09:26,701][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:09:27,209][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:09:27,718][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:09:28,226][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:09:28,734][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:09:29,242][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:09:29,751][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:09:30,259][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:09:30,767][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:09:31,275][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:09:31,784][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:09:32,292][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:09:32,802][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:09:33,312][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:09:33,820][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:09:34,329][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:09:34,838][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:09:35,346][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:09:35,854][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:09:36,361][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:09:36,869][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:09:37,376][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:09:37,884][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:09:38,391][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:09:38,899][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:09:39,407][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:09:39,913][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:09:40,421][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:09:40,929][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:09:41,436][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:09:41,942][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:09:42,450][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:09:42,958][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:09:43,465][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:09:43,973][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:09:44,481][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:09:44,987][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:09:45,494][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:09:46,002][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:09:46,508][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 22:09:47,167][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 22:09:47,924][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:09:47,926][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:09:47,927][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:09:48,785][__main__][INFO] - Iteration 299 took 1m 15s (8.78% Gen, 90.08% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 19m 53s. Estimated total time: 62h 54m 28s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 48s, 500 more iterations: 10h 29m 4s. [2026-03-25 22:09:48,787][__main__][INFO] - Starting iteration 299. [2026-03-25 22:09:49,196][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 22:09:49,197][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:09:50,562][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:09:51,593][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:09:52,146][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:09:56,423][__main__][INFO] - Number of regex retries in iteration 299: 3 [2026-03-25 22:09:56,424][__main__][INFO] - agents played in iteration 299 are Bob, Alice [2026-03-25 22:09:57,384][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:09:58,014][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:09:58,480][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:09:58,995][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:09:59,505][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:10:00,014][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:10:00,524][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:10:01,035][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:10:01,543][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:10:02,054][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:10:02,562][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:10:03,070][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:10:03,578][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:10:04,087][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:10:04,595][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:10:05,103][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:10:05,610][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:10:06,119][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:10:06,628][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:10:07,136][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:10:07,642][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:10:08,150][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:10:08,658][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:10:09,165][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:10:09,672][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:10:10,182][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:10:10,690][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:10:11,198][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:10:11,707][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:10:12,215][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:10:12,722][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:10:13,231][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:10:13,740][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:10:14,248][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:10:14,756][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:10:15,265][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:10:15,771][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:10:16,279][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:10:16,787][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:10:17,293][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:10:17,802][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:10:18,310][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:10:18,819][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:10:19,328][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:10:19,837][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:10:20,346][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:10:20,856][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:10:21,365][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:10:21,874][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:10:22,383][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:10:22,891][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:10:23,399][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:10:23,907][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:10:24,416][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:10:24,923][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:10:25,431][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:10:25,939][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:10:26,449][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:10:26,957][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:10:27,465][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:10:27,972][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:10:28,481][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:10:28,989][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:10:29,499][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:10:30,008][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:10:30,516][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:10:31,026][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:10:31,536][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:10:32,046][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:10:32,556][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:10:33,066][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:10:33,575][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:10:34,085][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:10:34,594][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:10:35,104][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:10:35,613][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:10:36,121][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:10:36,630][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:10:37,139][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:10:37,648][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:10:38,156][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:10:38,665][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:10:39,173][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:10:39,679][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:10:40,187][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:10:40,693][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:10:41,201][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:10:41,708][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:10:42,212][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:10:42,721][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:10:43,231][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:10:43,739][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:10:44,248][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:10:44,756][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:10:45,265][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:10:45,773][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:10:46,282][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:10:46,790][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:10:47,300][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:10:47,808][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:10:48,316][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:10:48,824][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:10:49,333][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:10:49,841][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:10:50,351][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:10:50,860][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:10:51,370][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:10:51,878][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:10:52,387][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:10:52,896][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:10:53,404][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:10:53,911][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:10:54,422][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:10:54,931][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:10:55,438][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:10:55,945][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:10:56,452][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:10:56,959][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:10:57,466][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:10:57,973][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:10:58,482][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:10:58,989][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:10:59,497][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:11:00,005][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:11:00,512][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:11:01,022][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:11:01,530][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:11:02,038][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:11:02,547][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:11:03,055][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21642 tokens. [2026-03-25 22:11:03,728][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-25 22:11:04,483][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:11:04,485][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:11:04,487][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:11:05,158][__main__][INFO] - Iteration 300 took 1m 15s (9.51% Gen, 89.60% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 56h 42m 15s. Estimated total time: 63h 18m 7s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 36s, 500 more iterations: 10h 33m 1s. [2026-03-25 22:11:05,160][__main__][INFO] - Starting iteration 300. [2026-03-25 22:11:05,562][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 5 and human policies 1. [2026-03-25 22:11:05,563][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:11:06,179][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:11:12,077][__main__][INFO] - Number of regex retries in iteration 300: 1 [2026-03-25 22:11:12,078][__main__][INFO] - agents played in iteration 300 are Bob, Alice [2026-03-25 22:11:13,052][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:11:13,692][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:11:14,158][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:11:14,673][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:11:15,183][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:11:15,691][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:11:16,201][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:11:16,710][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:11:17,220][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:11:17,729][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:11:18,238][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:11:18,747][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:11:19,254][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:11:19,763][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:11:20,272][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:11:20,780][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:11:21,287][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:11:21,796][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:11:22,304][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:11:22,813][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:11:23,322][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:11:23,830][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:11:24,338][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:11:24,846][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:11:25,354][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:11:25,862][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:11:26,375][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:11:26,883][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:11:27,392][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:11:27,901][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:11:28,410][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:11:28,918][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:11:29,428][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:11:29,938][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:11:30,450][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:11:30,969][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:11:31,481][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:11:31,991][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:11:32,503][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:11:33,014][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:11:33,525][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:11:34,034][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:11:34,543][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:11:35,051][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:11:35,560][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:11:36,069][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:11:36,577][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:11:37,086][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:11:37,594][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:11:38,104][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:11:38,612][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:11:39,121][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:11:39,629][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:11:40,137][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:11:40,645][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:11:41,154][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:11:41,661][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:11:42,168][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:11:42,676][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:11:43,185][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:11:43,692][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:11:44,201][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:11:44,710][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:11:45,218][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:11:45,729][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:11:46,239][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:11:46,748][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:11:47,257][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:11:47,766][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:11:48,276][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:11:48,786][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:11:49,295][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:11:49,804][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:11:50,314][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:11:50,823][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:11:51,332][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:11:51,840][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:11:52,349][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:11:52,856][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:11:53,365][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:11:53,873][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:11:54,381][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:11:54,889][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:11:55,396][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:11:55,905][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:11:56,413][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:11:56,921][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:11:57,429][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:11:57,937][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:11:58,445][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:11:58,952][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:11:59,460][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:11:59,968][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:12:00,476][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:12:00,983][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:12:01,490][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:12:01,997][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:12:02,505][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:12:03,014][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:12:03,523][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:12:04,033][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:12:04,543][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:12:05,052][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:12:05,562][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:12:06,073][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:12:06,583][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:12:07,090][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:12:07,598][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:12:08,105][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:12:08,613][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:12:09,121][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:12:09,629][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:12:10,137][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:12:10,645][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:12:11,152][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:12:11,659][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:12:12,165][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:12:12,672][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:12:13,179][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:12:13,686][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:12:14,193][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:12:14,701][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:12:15,208][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:12:15,716][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:12:16,226][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:12:16,735][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:12:17,243][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:12:17,751][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:12:18,261][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:12:18,770][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 22:12:19,443][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-25 22:12:20,204][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:12:20,207][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:12:20,208][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:12:21,759][__main__][INFO] - Iteration 301 took 1m 16s (8.55% Gen, 89.41% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 52m 43s. Estimated total time: 63h 29m 51s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 59s, 500 more iterations: 10h 34m 58s. [2026-03-25 22:12:21,761][__main__][INFO] - Starting iteration 301. [2026-03-25 22:12:22,164][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:12:22,165][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:12:22,795][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:12:28,865][__main__][INFO] - Number of regex retries in iteration 301: 1 [2026-03-25 22:12:28,866][__main__][INFO] - agents played in iteration 301 are Bob, Alice [2026-03-25 22:12:29,838][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:12:30,467][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:12:30,934][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:12:31,446][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:12:31,954][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:12:32,462][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:12:32,970][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:12:33,479][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:12:33,987][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:12:34,495][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:12:35,003][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:12:35,511][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:12:36,020][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:12:36,529][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:12:37,038][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:12:37,547][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:12:38,056][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:12:38,564][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:12:39,075][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:12:39,584][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:12:40,094][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:12:40,602][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:12:41,111][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:12:41,620][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:12:42,129][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:12:42,639][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:12:43,147][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:12:43,655][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:12:44,163][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:12:44,671][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:12:45,179][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:12:45,687][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:12:46,194][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:12:46,704][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:12:47,212][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:12:47,720][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:12:48,228][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:12:48,738][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:12:49,246][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:12:49,755][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:12:50,264][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:12:50,772][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:12:51,280][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:12:51,788][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:12:52,296][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:12:52,804][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:12:53,312][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:12:53,821][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:12:54,329][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:12:54,837][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:12:55,353][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:12:55,861][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:12:56,369][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:12:56,878][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:12:57,386][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:12:57,893][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:12:58,402][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:12:58,911][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:12:59,421][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:12:59,931][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:13:00,448][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:13:00,958][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:13:01,468][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:13:01,977][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:13:02,486][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:13:02,994][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:13:03,504][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:13:04,013][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:13:04,524][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:13:05,032][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:13:05,542][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:13:06,052][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:13:06,560][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:13:07,069][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:13:07,579][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:13:08,088][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:13:08,596][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:13:09,106][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:13:09,615][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:13:10,123][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:13:10,632][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:13:11,142][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:13:11,650][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:13:12,160][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:13:12,669][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:13:13,179][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:13:13,687][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:13:14,195][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:13:14,705][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:13:15,216][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:13:15,724][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:13:16,231][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:13:16,739][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:13:17,247][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:13:17,754][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:13:18,261][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:13:18,769][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:13:19,276][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:13:19,784][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:13:20,292][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:13:20,801][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:13:21,310][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:13:21,818][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:13:22,326][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:13:22,836][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:13:23,343][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:13:23,852][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:13:24,361][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:13:24,870][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:13:25,379][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:13:25,887][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:13:26,396][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:13:26,905][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:13:27,414][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:13:27,920][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:13:28,427][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:13:28,933][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:13:29,439][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:13:29,946][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:13:30,452][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:13:30,959][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:13:31,464][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:13:31,972][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:13:32,481][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:13:32,990][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:13:33,497][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:13:34,006][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:13:34,514][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:13:35,023][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:13:35,531][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 22:13:36,200][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 22:13:36,957][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:13:36,959][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:13:36,961][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:13:37,750][__main__][INFO] - Iteration 302 took 1m 15s (8.87% Gen, 90.09% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 20m 55s. Estimated total time: 62h 59m 20s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 58s, 500 more iterations: 10h 29m 53s. [2026-03-25 22:13:37,752][__main__][INFO] - Starting iteration 302. [2026-03-25 22:13:38,155][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:13:38,155][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:13:40,520][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:13:41,183][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:13:44,960][__main__][INFO] - Number of regex retries in iteration 302: 2 [2026-03-25 22:13:44,961][__main__][INFO] - agents played in iteration 302 are Bob, Alice [2026-03-25 22:13:45,879][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:13:46,516][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:13:46,981][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:13:47,493][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:13:48,002][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:13:48,510][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:13:49,018][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:13:49,525][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:13:50,032][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:13:50,540][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:13:51,051][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:13:51,559][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:13:52,067][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:13:52,575][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:13:53,083][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:13:53,591][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:13:54,101][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:13:54,610][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:13:55,121][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:13:55,631][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:13:56,142][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:13:56,654][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:13:57,163][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:13:57,672][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:13:58,182][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:13:58,692][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:13:59,201][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:13:59,709][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:14:00,219][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:14:00,728][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:14:01,236][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:14:01,745][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:14:02,254][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:14:02,762][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:14:03,271][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:14:03,781][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:14:04,291][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:14:04,801][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:14:05,311][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:14:05,822][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:14:06,332][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:14:06,842][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:14:07,350][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:14:07,859][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:14:08,363][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:14:08,871][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:14:09,380][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:14:09,888][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:14:10,395][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:14:10,912][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:14:11,422][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:14:11,931][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:14:12,440][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:14:12,950][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:14:13,458][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:14:13,967][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:14:14,474][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:14:14,983][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:14:15,492][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:14:16,008][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:14:16,516][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:14:17,027][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:14:17,537][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:14:18,046][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:14:18,555][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:14:19,064][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:14:19,571][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:14:20,080][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:14:20,588][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:14:21,095][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:14:21,603][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:14:22,110][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:14:22,619][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:14:23,126][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:14:23,634][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:14:24,143][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:14:24,652][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:14:25,159][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:14:25,667][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:14:26,174][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:14:26,683][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:14:27,192][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:14:27,702][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:14:28,211][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:14:28,721][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:14:29,231][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:14:29,742][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:14:30,252][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:14:30,762][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:14:31,271][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:14:31,780][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:14:32,287][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:14:32,795][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:14:33,302][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:14:33,810][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:14:34,318][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:14:34,826][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:14:35,334][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:14:35,844][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:14:36,354][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:14:36,864][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:14:37,373][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:14:37,995][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:14:38,503][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:14:39,012][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:14:39,523][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:14:40,032][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:14:40,540][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:14:41,047][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:14:41,555][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:14:42,063][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:14:42,572][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:14:43,079][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:14:43,586][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:14:44,095][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:14:44,604][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:14:45,112][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:14:45,621][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:14:46,128][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:14:46,636][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:14:47,144][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:14:47,651][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:14:48,161][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:14:48,669][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:14:49,177][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:14:49,685][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:14:50,193][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:14:50,701][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:14:51,210][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:14:51,719][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21730 tokens. [2026-03-25 22:14:52,401][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.38%, ΔTime: 00:01:05 [2026-03-25 22:14:53,177][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:14:53,179][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:14:53,181][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:14:53,936][__main__][INFO] - Iteration 303 took 1m 15s (8.98% Gen, 90.02% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 29m 24s. Estimated total time: 63h 9m 5s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 18s, 500 more iterations: 10h 31m 30s. [2026-03-25 22:14:53,941][__main__][INFO] - Starting iteration 303. [2026-03-25 22:14:54,343][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:14:54,344][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:14:55,083][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:15:01,671][__main__][INFO] - Number of regex retries in iteration 303: 1 [2026-03-25 22:15:01,672][__main__][INFO] - agents played in iteration 303 are Bob, Alice [2026-03-25 22:15:02,700][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:15:03,354][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:15:03,819][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:15:04,332][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:15:04,842][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:15:05,350][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:15:05,859][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:15:06,368][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:15:06,875][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:15:07,383][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:15:07,891][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:15:08,401][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:15:08,909][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:15:09,418][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:15:09,926][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:15:10,435][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:15:10,943][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:15:11,452][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:15:11,964][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:15:12,474][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:15:12,983][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:15:13,493][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:15:14,003][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:15:14,513][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:15:15,022][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:15:15,532][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:15:16,041][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:15:16,549][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:15:17,056][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:15:17,564][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:15:18,072][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:15:18,580][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:15:19,088][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:15:19,597][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:15:20,101][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:15:20,606][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:15:21,110][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:15:21,615][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:15:22,121][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:15:22,625][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:15:23,130][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:15:23,634][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:15:24,143][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:15:24,652][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:15:25,160][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:15:25,670][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:15:26,179][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:15:26,687][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:15:27,195][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:15:27,705][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:15:28,214][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:15:28,722][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:15:29,231][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:15:29,740][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:15:30,248][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:15:30,756][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:15:31,264][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:15:31,772][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:15:32,281][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:15:32,789][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:15:33,298][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:15:33,808][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:15:34,316][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:15:34,826][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:15:35,335][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:15:35,845][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:15:36,352][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:15:36,860][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:15:37,368][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:15:37,875][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:15:38,384][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:15:38,892][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:15:39,402][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:15:39,910][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:15:40,418][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:15:40,928][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:15:41,439][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:15:41,948][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:15:42,457][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:15:42,967][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:15:43,476][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:15:43,986][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:15:44,494][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:15:45,004][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:15:45,514][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:15:46,032][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:15:46,543][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:15:47,052][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:15:47,563][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:15:48,072][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:15:48,582][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:15:49,092][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:15:49,601][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:15:50,111][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:15:50,621][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:15:51,131][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:15:51,641][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:15:52,150][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:15:52,656][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:15:53,162][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:15:53,667][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:15:54,173][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:15:54,679][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:15:55,184][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:15:55,688][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:15:56,193][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:15:56,702][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:15:57,211][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:15:57,723][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:15:58,233][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:15:58,743][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:15:59,251][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:15:59,761][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:16:00,271][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:16:00,779][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:16:01,287][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:16:01,794][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:16:02,302][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:16:02,810][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:16:03,318][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:16:03,827][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:16:04,336][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:16:04,845][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:16:05,354][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:16:05,863][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:16:06,371][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:16:06,880][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:16:07,387][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:16:07,896][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:16:08,404][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 22:16:09,076][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 22:16:09,842][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:16:09,844][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:16:09,846][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:16:10,598][__main__][INFO] - Iteration 304 took 1m 16s (9.61% Gen, 89.40% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 56h 51m 48s. Estimated total time: 63h 32m 45s. Time estimates for 10 more iterations: 12m 42s, 100 more iterations: 2h 7m 5s, 500 more iterations: 10h 35m 27s. [2026-03-25 22:16:10,600][__main__][INFO] - Starting iteration 304. [2026-03-25 22:16:11,002][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:16:11,002][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:16:17,784][__main__][INFO] - Number of regex retries in iteration 304: 0 [2026-03-25 22:16:17,785][__main__][INFO] - agents played in iteration 304 are Bob, Alice [2026-03-25 22:16:18,747][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:16:19,377][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:16:19,847][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:16:20,361][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:16:20,872][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:16:21,383][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:16:21,893][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:16:22,403][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:16:22,911][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:16:23,423][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:16:23,930][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:16:24,436][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:16:24,942][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:16:25,449][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:16:25,955][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:16:26,463][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:16:26,969][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:16:27,475][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:16:27,985][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:16:28,493][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:16:29,002][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:16:29,511][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:16:30,022][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:16:30,532][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:16:31,041][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:16:31,550][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:16:32,059][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:16:32,567][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:16:33,076][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:16:33,584][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:16:34,093][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:16:34,602][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:16:35,111][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:16:35,622][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:16:36,133][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:16:36,643][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:16:37,152][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:16:37,662][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:16:38,171][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:16:38,683][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:16:39,193][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:16:39,703][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:16:40,213][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:16:40,723][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:16:41,234][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:16:41,744][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:16:42,254][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:16:42,763][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:16:43,272][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:16:43,784][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:16:44,293][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:16:44,801][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:16:45,311][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:16:45,823][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:16:46,333][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:16:46,842][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:16:47,351][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:16:47,862][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:16:48,371][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:16:48,879][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:16:49,388][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:16:49,897][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:16:50,405][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:16:50,913][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:16:51,424][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:16:51,934][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:16:52,443][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:16:52,953][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:16:53,462][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:16:53,971][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:16:54,481][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:16:54,991][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:16:55,501][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:16:56,011][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:16:56,518][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:16:57,025][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:16:57,533][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:16:58,039][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:16:58,547][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:16:59,053][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:16:59,560][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:17:00,066][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:17:00,575][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:17:01,091][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:17:01,601][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:17:02,110][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:17:02,623][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:17:03,133][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:17:03,643][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:17:04,153][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:17:04,663][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:17:05,172][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:17:05,687][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:17:06,197][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:17:06,707][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:17:07,216][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:17:07,725][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:17:08,234][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:17:08,744][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:17:09,253][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:17:09,763][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:17:10,272][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:17:10,785][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:17:11,294][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:17:11,804][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:17:12,313][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:17:12,825][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:17:13,334][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:17:13,845][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:17:14,354][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:17:14,864][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:17:15,374][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:17:15,883][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:17:16,393][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:17:16,903][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:17:17,413][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:17:17,923][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:17:18,432][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:17:18,943][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:17:19,452][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:17:19,962][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:17:20,472][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:17:20,982][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:17:21,492][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:17:22,001][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:17:22,510][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:17:23,020][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:17:23,529][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:17:24,039][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:17:24,548][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-25 22:17:25,215][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 22:17:25,982][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:17:25,985][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:17:25,986][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:17:26,729][__main__][INFO] - Iteration 305 took 1m 15s (8.96% Gen, 90.06% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 24m 9s. Estimated total time: 63h 6m 22s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 12s, 500 more iterations: 10h 31m 3s. [2026-03-25 22:17:26,731][__main__][INFO] - Starting iteration 305. [2026-03-25 22:17:27,133][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:17:27,134][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:17:27,749][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:17:33,854][__main__][INFO] - Number of regex retries in iteration 305: 1 [2026-03-25 22:17:33,855][__main__][INFO] - agents played in iteration 305 are Bob, Alice [2026-03-25 22:17:34,808][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:17:35,434][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:17:35,898][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:17:36,410][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:17:36,919][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:17:37,428][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:17:37,936][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:17:38,443][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:17:38,951][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:17:39,460][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:17:39,972][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:17:40,480][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:17:40,989][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:17:41,498][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:17:42,007][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:17:42,516][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:17:43,026][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:17:43,535][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:17:44,043][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:17:44,550][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:17:45,058][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:17:45,565][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:17:46,072][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:17:46,580][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:17:47,087][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:17:47,594][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:17:48,103][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:17:48,612][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:17:49,120][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:17:49,628][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:17:50,136][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:17:50,644][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:17:51,152][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:17:51,659][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:17:52,167][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:17:52,677][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:17:53,186][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:17:53,695][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:17:54,205][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:17:54,715][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:17:55,224][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:17:55,733][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:17:56,244][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:17:56,753][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:17:57,262][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:17:57,771][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:17:58,280][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:17:58,789][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:17:59,298][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:17:59,807][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:18:00,316][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:18:00,823][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:18:01,332][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:18:01,841][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:18:02,349][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:18:02,857][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:18:03,363][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:18:03,872][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:18:04,382][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:18:04,891][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:18:05,401][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:18:05,910][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:18:06,420][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:18:06,929][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:18:07,438][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:18:07,948][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:18:08,456][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:18:08,963][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:18:09,470][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:18:09,979][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:18:10,486][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:18:10,994][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:18:11,502][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:18:12,012][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:18:12,520][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:18:13,029][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:18:13,539][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:18:14,049][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:18:14,557][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:18:15,066][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:18:15,575][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:18:16,084][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:18:16,591][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:18:17,097][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:18:17,604][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:18:18,111][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:18:18,618][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:18:19,123][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:18:19,632][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:18:20,140][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:18:20,648][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:18:21,156][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:18:21,663][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:18:22,171][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:18:22,678][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:18:23,186][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:18:23,693][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:18:24,202][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:18:24,711][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:18:25,223][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:18:25,733][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:18:26,241][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:18:26,750][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:18:27,260][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:18:27,767][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:18:28,274][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:18:28,794][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:18:29,311][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:18:29,825][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:18:30,337][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:18:30,849][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:18:31,360][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:18:31,870][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:18:32,381][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:18:32,890][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:18:33,398][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:18:33,908][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:18:34,417][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:18:34,926][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:18:35,435][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:18:35,945][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:18:36,454][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:18:36,965][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:18:37,474][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:18:37,984][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:18:38,495][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:18:39,004][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:18:39,523][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:18:40,038][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:18:40,550][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21727 tokens. [2026-03-25 22:18:41,215][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.65%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 22:18:41,972][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:18:41,975][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:18:41,976][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:18:42,719][__main__][INFO] - Iteration 306 took 1m 15s (8.89% Gen, 90.12% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 15m 48s. Estimated total time: 62h 59m 18s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 58s, 500 more iterations: 10h 29m 53s. [2026-03-25 22:18:42,721][__main__][INFO] - Starting iteration 306. [2026-03-25 22:18:43,129][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:18:43,129][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:18:46,547][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 books, 10 hats, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:18:50,139][__main__][INFO] - Number of regex retries in iteration 306: 1 [2026-03-25 22:18:50,140][__main__][INFO] - agents played in iteration 306 are Bob, Alice [2026-03-25 22:18:51,113][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:18:51,747][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:18:52,213][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:18:52,727][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:18:53,236][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:18:53,746][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:18:54,254][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:18:54,764][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:18:55,272][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:18:55,781][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:18:56,289][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:18:56,799][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:18:57,308][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:18:57,817][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:18:58,326][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:18:58,835][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:18:59,346][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:18:59,855][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:19:00,367][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:19:00,877][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:19:01,386][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:19:01,894][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:19:02,403][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:19:02,912][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:19:03,421][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:19:03,930][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:19:04,439][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:19:04,948][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:19:05,457][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:19:05,966][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:19:06,474][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:19:06,983][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:19:07,491][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:19:08,001][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:19:08,509][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:19:09,017][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:19:09,526][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:19:10,034][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:19:10,542][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:19:11,050][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:19:11,559][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:19:12,067][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:19:12,578][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:19:13,087][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:19:13,598][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:19:14,107][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:19:14,616][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:19:15,126][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:19:15,635][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:19:16,144][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:19:16,653][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:19:17,162][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:19:17,680][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:19:18,190][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:19:18,702][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:19:19,215][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:19:19,725][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:19:20,235][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:19:20,743][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:19:21,251][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:19:21,760][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:19:22,267][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:19:22,775][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:19:23,283][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:19:23,791][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:19:24,299][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:19:24,806][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:19:25,313][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:19:25,822][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:19:26,330][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:19:26,838][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:19:27,346][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:19:27,854][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:19:28,362][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:19:28,871][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:19:29,379][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:19:29,886][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:19:30,395][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:19:30,903][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:19:31,412][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:19:31,921][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:19:32,429][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:19:32,940][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:19:33,449][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:19:33,957][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:19:34,466][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:19:34,975][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:19:35,484][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:19:35,993][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:19:36,503][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:19:37,012][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:19:37,521][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:19:38,030][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:19:38,539][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:19:39,047][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:19:39,555][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:19:40,064][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:19:40,573][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:19:41,080][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:19:41,589][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:19:42,097][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:19:42,605][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:19:43,113][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:19:43,624][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:19:44,134][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:19:44,642][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:19:45,152][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:19:45,662][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:19:46,171][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:19:46,680][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:19:47,189][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:19:47,699][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:19:48,208][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:19:48,717][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:19:49,227][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:19:49,735][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:19:50,244][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:19:50,752][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:19:51,261][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:19:51,769][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:19:52,278][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:19:52,786][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:19:53,293][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:19:53,800][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:19:54,307][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:19:54,814][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:19:55,322][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:19:55,830][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:19:56,336][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:19:56,843][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21740 tokens. [2026-03-25 22:19:57,498][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.16%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 22:19:58,268][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:19:58,271][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:19:58,272][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:19:59,018][__main__][INFO] - Iteration 307 took 1m 15s (9.24% Gen, 89.78% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 56h 29m 43s. Estimated total time: 63h 14m 29s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 28s, 500 more iterations: 10h 32m 24s. [2026-03-25 22:19:59,020][__main__][INFO] - Starting iteration 307. [2026-03-25 22:19:59,423][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:19:59,424][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:20:06,286][__main__][INFO] - Number of regex retries in iteration 307: 0 [2026-03-25 22:20:06,287][__main__][INFO] - agents played in iteration 307 are Bob, Alice [2026-03-25 22:20:07,254][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:20:07,878][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:20:08,342][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:20:08,855][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:20:09,363][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:20:09,871][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:20:10,380][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:20:10,889][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:20:11,398][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:20:11,907][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:20:12,415][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:20:12,923][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:20:13,439][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:20:13,948][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:20:14,457][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:20:14,965][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:20:15,473][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:20:15,986][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:20:16,496][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:20:17,005][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:20:17,514][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:20:18,024][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:20:18,535][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:20:19,044][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:20:19,553][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:20:20,061][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:20:20,570][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:20:21,079][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:20:21,588][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:20:22,096][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:20:22,605][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:20:23,114][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:20:23,623][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:20:24,132][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:20:24,644][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:20:25,154][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:20:25,663][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:20:26,173][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:20:26,682][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:20:27,190][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:20:27,700][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:20:28,209][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:20:28,721][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:20:29,231][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:20:29,740][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:20:30,249][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:20:30,758][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:20:31,267][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:20:31,777][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:20:32,286][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:20:32,793][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:20:33,303][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:20:33,811][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:20:34,319][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:20:34,827][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:20:35,335][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:20:35,843][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:20:36,352][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:20:36,860][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:20:37,369][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:20:37,877][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:20:38,386][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:20:38,894][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:20:39,403][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:20:39,911][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:20:40,420][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:20:40,928][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:20:41,436][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:20:41,944][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:20:42,453][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:20:42,961][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:20:43,470][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:20:43,978][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:20:44,486][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:20:44,993][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:20:45,502][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:20:46,010][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:20:46,518][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:20:47,026][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:20:47,534][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:20:48,042][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:20:48,549][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:20:49,056][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:20:49,565][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:20:50,073][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:20:50,580][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:20:51,088][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:20:51,596][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:20:52,104][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:20:52,612][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:20:53,121][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:20:53,629][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:20:54,137][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:20:54,645][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:20:55,153][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:20:55,662][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:20:56,170][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:20:56,678][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:20:57,186][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:20:57,694][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:20:58,203][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:20:58,711][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:20:59,222][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:20:59,731][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:21:00,240][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:21:00,749][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:21:01,258][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:21:01,767][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:21:02,276][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:21:02,785][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:21:03,294][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:21:03,803][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:21:04,311][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:21:04,823][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:21:05,331][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:21:05,839][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:21:06,347][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:21:06,855][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:21:07,363][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:21:07,870][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:21:08,377][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:21:08,885][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:21:09,394][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:21:09,902][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:21:10,411][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:21:10,920][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:21:11,429][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:21:11,937][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:21:12,445][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:21:12,954][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 22:21:13,621][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 22:21:14,382][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:21:14,387][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:21:14,389][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:21:15,136][__main__][INFO] - Iteration 308 took 1m 15s (9.06% Gen, 89.95% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 19m 37s. Estimated total time: 63h 5m 39s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 11s, 500 more iterations: 10h 30m 56s. [2026-03-25 22:21:15,138][__main__][INFO] - Starting iteration 308. [2026-03-25 22:21:15,542][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:21:15,543][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:21:18,590][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:21:22,747][__main__][INFO] - Number of regex retries in iteration 308: 1 [2026-03-25 22:21:22,748][__main__][INFO] - agents played in iteration 308 are Bob, Alice [2026-03-25 22:21:23,711][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:21:24,341][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:21:24,806][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:21:25,319][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:21:25,828][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:21:26,337][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:21:26,845][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:21:27,354][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:21:27,862][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:21:28,371][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:21:28,878][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:21:29,386][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:21:29,893][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:21:30,402][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:21:30,909][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:21:31,418][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:21:31,926][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:21:32,434][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:21:32,945][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:21:33,455][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:21:33,964][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:21:34,472][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:21:34,981][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:21:35,490][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:21:36,000][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:21:36,509][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:21:37,018][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:21:37,527][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:21:38,036][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:21:38,545][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:21:39,054][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:21:39,563][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:21:40,072][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:21:40,581][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:21:41,093][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:21:41,604][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:21:42,113][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:21:42,623][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:21:43,133][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:21:43,643][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:21:44,153][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:21:44,663][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:21:45,172][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:21:45,680][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:21:46,189][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:21:46,697][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:21:47,206][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:21:47,714][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:21:48,224][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:21:48,734][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:21:49,242][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:21:49,752][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:21:50,261][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:21:50,770][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:21:51,279][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:21:51,787][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:21:52,296][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:21:52,805][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:21:53,312][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:21:53,822][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:21:54,331][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:21:54,838][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:21:55,346][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:21:55,854][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:21:56,363][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:21:56,871][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:21:57,380][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:21:57,888][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:21:58,397][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:21:58,906][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:21:59,413][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:21:59,922][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:22:00,431][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:22:00,939][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:22:01,446][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:22:01,953][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:22:02,462][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:22:02,970][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:22:03,478][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:22:03,986][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:22:04,493][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:22:05,002][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:22:05,511][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:22:06,021][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:22:06,531][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:22:07,041][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:22:07,550][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:22:08,060][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:22:08,569][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:22:09,078][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:22:09,586][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:22:10,093][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:22:10,600][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:22:11,108][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:22:11,617][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:22:12,125][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:22:12,633][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:22:13,143][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:22:13,653][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:22:14,162][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:22:14,671][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:22:15,182][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:22:15,692][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:22:16,201][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:22:16,711][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:22:17,222][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:22:17,731][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:22:18,240][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:22:18,749][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:22:19,259][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:22:19,768][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:22:20,276][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:22:20,784][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:22:21,293][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:22:21,804][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:22:22,313][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:22:22,824][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:22:23,334][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:22:23,844][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:22:24,353][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:22:24,862][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:22:25,372][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:22:25,882][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:22:26,390][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:22:26,896][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:22:27,405][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:22:27,912][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:22:28,421][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:22:28,929][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:22:29,436][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21700 tokens. [2026-03-25 22:22:30,106][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:05 [2026-03-25 22:22:30,859][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:22:30,861][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:22:30,863][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:22:31,574][__main__][INFO] - Iteration 309 took 1m 16s (9.48% Gen, 89.59% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 56h 34m 20s. Estimated total time: 63h 21m 38s. Time estimates for 10 more iterations: 12m 40s, 100 more iterations: 2h 6m 43s, 500 more iterations: 10h 33m 36s. [2026-03-25 22:22:31,577][__main__][INFO] - Starting iteration 309. [2026-03-25 22:22:31,983][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:22:31,983][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:22:33,268][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:22:38,227][__main__][INFO] - Number of regex retries in iteration 309: 1 [2026-03-25 22:22:38,228][__main__][INFO] - agents played in iteration 309 are Bob, Alice [2026-03-25 22:22:39,186][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:22:40,116][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:22:40,580][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:22:41,092][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:22:41,599][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:22:42,108][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:22:42,615][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:22:43,123][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:22:43,632][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:22:44,141][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:22:44,650][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:22:45,157][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:22:45,664][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:22:46,172][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:22:46,680][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:22:47,188][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:22:47,695][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:22:48,203][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:22:48,714][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:22:49,223][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:22:49,733][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:22:50,244][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:22:50,754][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:22:51,263][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:22:51,772][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:22:52,282][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:22:52,791][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:22:53,301][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:22:53,810][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:22:54,321][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:22:54,831][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:22:55,341][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:22:55,850][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:22:56,357][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:22:56,864][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:22:57,371][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:22:57,881][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:22:58,391][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:22:58,900][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:22:59,409][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:22:59,919][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:23:00,428][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:23:00,936][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:23:01,444][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:23:01,952][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:23:02,459][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:23:02,967][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:23:03,474][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:23:03,983][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:23:04,491][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:23:04,999][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:23:05,507][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:23:06,016][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:23:06,523][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:23:07,032][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:23:07,541][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:23:08,049][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:23:08,557][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:23:09,064][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:23:09,572][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:23:10,079][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:23:10,587][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:23:11,095][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:23:11,603][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:23:12,111][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:23:12,619][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:23:13,127][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:23:13,635][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:23:14,142][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:23:14,650][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:23:15,157][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:23:15,664][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:23:16,172][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:23:16,678][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:23:17,186][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:23:17,694][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:23:18,203][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:23:18,711][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:23:19,221][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:23:19,731][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:23:20,239][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:23:20,747][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:23:21,258][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:23:21,767][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:23:22,277][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:23:22,787][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:23:23,296][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:23:23,805][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:23:24,314][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:23:24,825][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:23:25,335][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:23:25,844][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:23:26,353][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:23:26,863][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:23:27,372][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:23:27,881][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:23:28,390][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:23:28,899][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:23:29,408][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:23:29,917][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:23:30,427][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:23:30,937][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:23:31,447][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:23:31,956][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:23:32,466][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:23:32,975][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:23:33,483][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:23:33,990][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:23:34,498][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:23:35,005][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:23:35,512][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:23:36,020][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:23:36,525][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:23:37,033][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:23:37,541][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:23:38,047][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:23:38,554][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:23:39,061][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:23:39,568][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:23:40,075][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:23:40,583][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:23:41,090][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:23:41,597][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:23:42,113][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:23:42,623][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:23:43,133][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:23:43,643][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:23:44,152][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:23:44,662][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:23:45,170][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21739 tokens. [2026-03-25 22:23:45,839][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 22:23:46,603][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:23:46,606][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:23:46,608][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:23:47,323][__main__][INFO] - Iteration 310 took 1m 15s (8.29% Gen, 90.76% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 58m 31s. Estimated total time: 62h 47m 5s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 34s, 500 more iterations: 10h 27m 50s. [2026-03-25 22:23:47,325][__main__][INFO] - Starting iteration 310. [2026-03-25 22:23:47,728][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:23:47,729][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:23:48,382][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:23:55,070][__main__][INFO] - Number of regex retries in iteration 310: 1 [2026-03-25 22:23:55,071][__main__][INFO] - agents played in iteration 310 are Bob, Alice [2026-03-25 22:23:56,040][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:23:56,675][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:23:57,140][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:23:57,654][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:23:58,163][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:23:58,672][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:23:59,181][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:23:59,689][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:24:00,198][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:24:00,707][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:24:01,215][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:24:01,723][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:24:02,232][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:24:02,741][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:24:03,249][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:24:03,758][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:24:04,266][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:24:04,775][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:24:05,284][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:24:05,792][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:24:06,299][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:24:06,809][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:24:07,317][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:24:07,826][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:24:08,334][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:24:08,842][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:24:09,351][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:24:09,860][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:24:10,369][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:24:10,876][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:24:11,384][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:24:11,892][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:24:12,401][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:24:12,909][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:24:13,420][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:24:13,929][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:24:14,437][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:24:14,947][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:24:15,456][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:24:15,965][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:24:16,473][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:24:16,983][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:24:17,490][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:24:17,998][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:24:18,505][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:24:19,013][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:24:19,522][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:24:20,030][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:24:20,539][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:24:21,049][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:24:21,557][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:24:22,066][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:24:22,574][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:24:23,083][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:24:23,592][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:24:24,102][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:24:24,611][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:24:25,120][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:24:25,629][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:24:26,137][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:24:26,646][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:24:27,155][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:24:27,664][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:24:28,172][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:24:28,681][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:24:29,189][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:24:29,697][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:24:30,207][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:24:30,715][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:24:31,224][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:24:31,732][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:24:32,242][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:24:32,751][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:24:33,259][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:24:33,767][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:24:34,275][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:24:34,784][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:24:35,292][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:24:35,801][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:24:36,311][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:24:36,820][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:24:37,329][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:24:37,838][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:24:38,347][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:24:38,854][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:24:39,364][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:24:39,872][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:24:40,380][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:24:40,887][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:24:41,395][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:24:41,903][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:24:42,412][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:24:42,921][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:24:43,429][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:24:43,937][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:24:44,445][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:24:44,953][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:24:45,462][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:24:45,973][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:24:46,482][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:24:46,991][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:24:47,503][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:24:48,013][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:24:48,524][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:24:49,033][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:24:49,543][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:24:50,051][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:24:50,558][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:24:51,066][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:24:51,574][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:24:52,080][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:24:52,587][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:24:53,096][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:24:53,604][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:24:54,112][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:24:54,623][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:24:55,133][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:24:55,643][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:24:56,153][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:24:56,663][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:24:57,172][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:24:57,681][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:24:58,189][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:24:58,698][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:24:59,206][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:24:59,715][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:25:00,224][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:25:00,732][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:25:01,242][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:25:01,751][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 22:25:02,423][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 22:25:03,192][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:25:03,194][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:25:03,196][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:25:03,994][__main__][INFO] - Iteration 311 took 1m 16s (9.63% Gen, 89.32% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 56h 43m 30s. Estimated total time: 63h 33m 20s. Time estimates for 10 more iterations: 12m 42s, 100 more iterations: 2h 7m 6s, 500 more iterations: 10h 35m 33s. [2026-03-25 22:25:03,996][__main__][INFO] - Starting iteration 311. [2026-03-25 22:25:04,398][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:25:04,398][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:25:06,619][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:25:11,362][__main__][INFO] - Number of regex retries in iteration 311: 1 [2026-03-25 22:25:11,363][__main__][INFO] - agents played in iteration 311 are Bob, Alice [2026-03-25 22:25:12,326][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:25:12,962][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:25:13,426][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:25:13,940][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:25:14,448][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:25:14,955][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:25:15,462][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:25:15,969][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:25:16,476][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:25:16,984][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:25:17,495][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:25:18,004][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:25:18,512][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:25:19,022][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:25:19,531][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:25:20,041][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:25:20,551][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:25:21,060][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:25:21,567][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:25:22,075][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:25:22,583][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:25:23,092][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:25:23,601][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:25:24,111][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:25:24,618][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:25:25,127][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:25:25,634][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:25:26,142][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:25:26,651][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:25:27,159][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:25:27,666][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:25:28,173][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:25:28,681][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:25:29,190][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:25:29,697][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:25:30,205][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:25:30,713][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:25:31,222][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:25:31,731][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:25:32,240][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:25:32,748][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:25:33,256][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:25:33,763][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:25:34,272][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:25:34,779][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:25:35,288][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:25:35,795][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:25:36,303][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:25:36,812][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:25:37,321][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:25:37,829][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:25:38,336][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:25:38,844][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:25:39,351][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:25:39,859][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:25:40,366][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:25:40,875][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:25:41,383][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:25:41,891][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:25:42,398][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:25:42,907][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:25:43,414][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:25:43,923][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:25:44,430][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:25:44,938][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:25:45,446][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:25:45,954][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:25:46,462][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:25:46,969][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:25:47,477][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:25:47,984][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:25:48,492][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:25:49,000][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:25:49,507][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:25:50,016][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:25:50,525][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:25:51,033][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:25:51,544][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:25:52,053][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:25:52,562][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:25:53,070][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:25:53,580][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:25:54,088][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:25:54,596][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:25:55,103][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:25:55,611][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:25:56,119][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:25:56,628][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:25:57,136][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:25:57,644][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:25:58,152][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:25:58,659][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:25:59,167][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:25:59,675][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:26:00,183][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:26:00,691][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:26:01,199][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:26:01,707][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:26:02,215][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:26:02,731][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:26:03,241][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:26:03,751][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:26:04,261][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:26:04,770][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:26:05,279][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:26:05,789][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:26:06,298][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:26:06,807][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:26:07,324][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:26:07,833][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:26:08,343][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:26:08,852][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:26:09,361][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:26:09,870][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:26:10,378][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:26:10,887][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:26:11,395][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:26:11,903][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:26:12,414][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:26:12,923][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:26:13,431][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:26:13,940][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:26:14,449][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:26:14,957][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:26:15,465][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:26:15,973][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:26:16,482][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:26:16,990][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:26:17,499][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:26:18,008][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 22:26:18,675][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 22:26:19,435][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:26:19,437][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:26:19,439][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:26:20,196][__main__][INFO] - Iteration 312 took 1m 15s (9.19% Gen, 89.81% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 18m 51s. Estimated total time: 63h 9m 58s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 19s, 500 more iterations: 10h 31m 39s. [2026-03-25 22:26:20,198][__main__][INFO] - Starting iteration 312. [2026-03-25 22:26:20,602][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:26:20,603][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:26:26,828][__main__][INFO] - Number of regex retries in iteration 312: 0 [2026-03-25 22:26:26,830][__main__][INFO] - agents played in iteration 312 are Bob, Alice [2026-03-25 22:26:28,091][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:26:28,717][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:26:29,180][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:26:29,691][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:26:30,200][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:26:30,706][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:26:31,212][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:26:31,721][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:26:32,229][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:26:32,735][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:26:33,245][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:26:33,756][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:26:34,263][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:26:34,775][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:26:35,283][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:26:35,793][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:26:36,302][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:26:36,813][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:26:37,321][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:26:37,832][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:26:38,340][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:26:38,846][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:26:39,354][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:26:39,864][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:26:40,372][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:26:40,881][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:26:41,388][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:26:41,897][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:26:42,404][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:26:42,912][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:26:43,420][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:26:43,928][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:26:44,435][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:26:44,943][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:26:45,450][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:26:45,961][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:26:46,469][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:26:46,979][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:26:47,487][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:26:47,997][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:26:48,505][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:26:49,016][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:26:49,526][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:26:50,034][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:26:50,543][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:26:51,051][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:26:51,558][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:26:52,066][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:26:52,573][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:26:53,082][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:26:53,588][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:26:54,096][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:26:54,603][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:26:55,112][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:26:55,619][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:26:56,128][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:26:56,635][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:26:57,144][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:26:57,652][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:26:58,162][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:26:58,669][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:26:59,180][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:26:59,687][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:27:00,197][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:27:00,705][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:27:01,214][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:27:01,723][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:27:02,229][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:27:02,736][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:27:03,244][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:27:03,751][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:27:04,257][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:27:04,764][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:27:05,272][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:27:05,780][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:27:06,288][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:27:06,797][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:27:07,305][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:27:07,815][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:27:08,323][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:27:08,833][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:27:09,343][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:27:09,852][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:27:10,362][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:27:10,869][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:27:11,378][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:27:11,884][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:27:12,393][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:27:12,901][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:27:13,411][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:27:13,917][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:27:14,422][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:27:14,926][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:27:15,433][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:27:15,939][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:27:16,446][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:27:16,958][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:27:17,466][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:27:17,972][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:27:18,483][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:27:18,991][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:27:19,500][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:27:20,009][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:27:20,520][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:27:21,031][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:27:21,540][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:27:22,050][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:27:22,559][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:27:23,068][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:27:23,578][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:27:24,087][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:27:24,597][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:27:25,106][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:27:25,616][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:27:26,124][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:27:26,631][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:27:27,145][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:27:27,653][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:27:28,163][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:27:28,670][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:27:29,179][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:27:29,688][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:27:30,197][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:27:30,708][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:27:31,217][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:27:31,735][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:27:32,246][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:27:32,755][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:27:33,265][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:27:33,774][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21718 tokens. [2026-03-25 22:27:34,442][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:05 [2026-03-25 22:27:35,196][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:27:35,198][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:27:35,200][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:27:35,928][__main__][INFO] - Iteration 313 took 1m 15s (8.27% Gen, 90.77% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 53m 58s. Estimated total time: 62h 46m 21s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 32s, 500 more iterations: 10h 27m 43s. [2026-03-25 22:27:35,931][__main__][INFO] - Starting iteration 313. [2026-03-25 22:27:36,334][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:27:36,335][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:27:43,135][__main__][INFO] - Number of regex retries in iteration 313: 0 [2026-03-25 22:27:43,136][__main__][INFO] - agents played in iteration 313 are Bob, Alice [2026-03-25 22:27:44,101][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:27:44,724][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:27:45,189][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:27:45,703][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:27:46,211][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:27:46,721][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:27:47,229][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:27:47,738][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:27:48,247][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:27:48,756][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:27:49,263][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:27:49,770][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:27:50,277][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:27:50,784][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:27:51,290][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:27:51,798][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:27:52,306][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:27:52,812][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:27:53,323][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:27:53,833][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:27:54,343][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:27:54,853][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:27:55,363][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:27:55,873][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:27:56,382][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:27:56,892][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:27:57,403][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:27:57,913][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:27:58,421][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:27:58,930][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:27:59,438][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:27:59,947][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:28:00,454][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:28:00,963][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:28:01,471][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:28:01,979][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:28:02,486][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:28:02,993][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:28:03,501][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:28:04,010][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:28:04,518][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:28:05,026][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:28:05,534][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:28:06,042][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:28:06,552][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:28:07,062][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:28:07,571][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:28:08,078][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:28:08,586][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:28:09,095][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:28:09,605][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:28:10,114][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:28:10,623][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:28:11,134][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:28:11,643][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:28:12,152][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:28:12,661][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:28:13,170][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:28:13,679][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:28:14,187][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:28:14,698][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:28:15,208][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:28:15,717][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:28:16,226][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:28:16,736][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:28:17,246][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:28:17,756][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:28:18,265][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:28:18,775][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:28:19,286][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:28:19,795][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:28:20,305][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:28:20,815][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:28:21,327][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:28:21,835][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:28:22,344][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:28:22,853][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:28:23,361][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:28:23,869][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:28:24,377][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:28:24,886][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:28:25,394][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:28:25,904][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:28:26,413][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:28:26,924][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:28:27,433][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:28:27,943][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:28:28,452][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:28:28,961][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:28:29,471][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:28:29,980][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:28:30,487][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:28:30,994][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:28:31,503][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:28:32,012][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:28:32,521][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:28:33,030][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:28:33,540][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:28:34,049][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:28:34,557][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:28:35,066][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:28:35,575][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:28:36,085][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:28:36,593][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:28:37,103][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:28:37,612][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:28:38,122][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:28:38,630][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:28:39,139][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:28:39,647][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:28:40,156][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:28:40,665][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:28:41,175][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:28:41,683][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:28:42,192][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:28:42,703][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:28:43,213][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:28:43,723][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:28:44,233][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:28:44,743][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:28:45,252][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:28:45,760][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:28:46,269][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:28:46,778][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:28:47,287][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:28:47,794][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:28:48,303][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:28:48,811][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:28:49,321][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:28:49,830][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 22:28:50,480][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 22:28:51,238][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:28:51,240][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:28:51,242][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:28:52,037][__main__][INFO] - Iteration 314 took 1m 15s (8.98% Gen, 89.96% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 11m 31s. Estimated total time: 63h 5m 10s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 10s, 500 more iterations: 10h 30m 51s. [2026-03-25 22:28:52,039][__main__][INFO] - Starting iteration 314. [2026-03-25 22:28:52,440][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:28:52,441][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:28:59,022][__main__][INFO] - Number of regex retries in iteration 314: 0 [2026-03-25 22:28:59,023][__main__][INFO] - agents played in iteration 314 are Bob, Alice [2026-03-25 22:28:59,988][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:29:00,618][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:29:01,082][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:29:01,595][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:29:02,103][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:29:02,612][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:29:03,122][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:29:03,632][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:29:04,140][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:29:04,649][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:29:05,159][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:29:05,668][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:29:06,176][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:29:06,685][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:29:07,194][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:29:07,704][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:29:08,213][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:29:08,725][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:29:09,235][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:29:09,744][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:29:10,253][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:29:10,764][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:29:11,274][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:29:11,784][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:29:12,293][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:29:12,803][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:29:13,315][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:29:13,826][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:29:14,337][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:29:14,848][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:29:15,358][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:29:15,868][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:29:16,378][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:29:16,888][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:29:17,396][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:29:17,906][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:29:18,416][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:29:18,925][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:29:19,433][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:29:19,943][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:29:20,452][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:29:20,961][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:29:21,470][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:29:21,980][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:29:22,489][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:29:22,999][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:29:23,507][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:29:24,017][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:29:24,526][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:29:25,036][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:29:25,544][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:29:26,053][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:29:26,561][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:29:27,069][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:29:27,577][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:29:28,085][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:29:28,592][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:29:29,104][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:29:29,614][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:29:30,123][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:29:30,633][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:29:31,143][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:29:31,652][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:29:32,162][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:29:32,671][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:29:33,181][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:29:33,690][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:29:34,199][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:29:34,708][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:29:35,218][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:29:35,727][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:29:36,236][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:29:36,745][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:29:37,254][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:29:37,763][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:29:38,272][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:29:38,781][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:29:39,289][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:29:39,797][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:29:40,307][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:29:40,816][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:29:41,326][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:29:41,835][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:29:42,344][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:29:42,853][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:29:43,361][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:29:43,870][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:29:44,380][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:29:44,888][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:29:45,396][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:29:45,906][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:29:46,416][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:29:46,926][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:29:47,436][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:29:47,946][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:29:48,455][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:29:48,965][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:29:49,474][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:29:49,982][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:29:50,490][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:29:50,997][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:29:51,505][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:29:52,013][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:29:52,521][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:29:53,029][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:29:53,537][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:29:54,046][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:29:54,554][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:29:55,062][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:29:55,570][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:29:56,077][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:29:56,585][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:29:57,093][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:29:57,602][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:29:58,109][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:29:58,617][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:29:59,124][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:29:59,632][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:30:00,140][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:30:00,648][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:30:01,155][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:30:01,663][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:30:02,171][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:30:02,680][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:30:03,188][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:30:03,697][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:30:04,205][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:30:04,713][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:30:05,223][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:30:05,733][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21740 tokens. [2026-03-25 22:30:06,395][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 22:30:07,151][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:30:07,154][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:30:07,157][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:30:07,882][__main__][INFO] - Iteration 315 took 1m 15s (8.72% Gen, 90.31% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 57m 13s. Estimated total time: 62h 52m 8s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 44s, 500 more iterations: 10h 28m 41s. [2026-03-25 22:30:07,884][__main__][INFO] - Starting iteration 315. [2026-03-25 22:30:08,288][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:30:08,288][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:30:08,896][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:30:15,228][__main__][INFO] - Number of regex retries in iteration 315: 1 [2026-03-25 22:30:15,229][__main__][INFO] - agents played in iteration 315 are Bob, Alice [2026-03-25 22:30:16,197][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:30:16,830][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:30:17,295][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:30:17,809][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:30:18,317][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:30:18,826][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:30:19,336][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:30:19,844][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:30:20,351][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:30:20,860][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:30:21,368][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:30:21,877][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:30:22,386][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:30:22,894][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:30:23,404][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:30:23,912][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:30:24,422][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:30:24,931][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:30:25,442][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:30:25,952][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:30:26,461][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:30:26,971][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:30:27,481][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:30:27,991][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:30:28,501][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:30:29,010][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:30:29,518][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:30:30,025][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:30:30,533][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:30:31,040][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:30:31,548][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:30:32,055][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:30:32,562][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:30:33,070][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:30:33,576][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:30:34,083][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:30:34,591][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:30:35,098][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:30:35,602][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:30:36,111][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:30:36,617][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:30:37,125][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:30:37,634][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:30:38,144][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:30:38,653][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:30:39,161][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:30:39,669][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:30:40,179][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:30:40,687][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:30:41,196][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:30:41,704][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:30:42,212][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:30:42,720][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:30:43,228][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:30:43,735][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:30:44,242][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:30:44,750][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:30:45,257][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:30:45,770][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:30:46,281][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:30:46,791][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:30:47,303][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:30:47,813][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:30:48,325][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:30:48,836][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:30:49,347][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:30:49,856][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:30:50,364][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:30:50,873][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:30:51,381][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:30:51,889][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:30:52,398][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:30:52,907][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:30:53,416][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:30:53,925][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:30:54,435][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:30:54,944][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:30:55,453][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:30:55,961][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:30:56,469][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:30:56,978][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:30:57,487][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:30:57,995][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:30:58,504][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:30:59,014][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:30:59,524][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:31:00,034][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:31:00,545][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:31:01,054][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:31:01,565][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:31:02,072][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:31:02,580][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:31:03,087][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:31:03,594][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:31:04,103][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:31:04,611][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:31:05,119][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:31:05,626][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:31:06,133][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:31:06,641][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:31:07,149][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:31:07,655][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:31:08,163][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:31:08,671][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:31:09,177][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:31:09,685][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:31:10,194][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:31:10,703][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:31:11,212][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:31:11,722][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:31:12,233][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:31:12,741][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:31:13,250][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:31:13,760][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:31:14,268][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:31:14,775][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:31:15,283][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:31:15,791][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:31:16,299][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:31:16,807][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:31:17,314][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:31:17,823][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:31:18,335][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:31:18,848][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:31:19,360][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:31:19,870][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:31:20,381][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:31:20,892][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:31:21,404][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:31:21,915][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21717 tokens. [2026-03-25 22:31:22,579][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.32%, Current % of VRAM taken: 60.68%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:05 [2026-03-25 22:31:23,331][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:31:23,333][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:31:23,334][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:31:24,009][__main__][INFO] - Iteration 316 took 1m 15s (9.17% Gen, 89.94% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 9m 56s. Estimated total time: 63h 6m 7s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 12s, 500 more iterations: 10h 31m 1s. [2026-03-25 22:31:24,012][__main__][INFO] - Starting iteration 316. [2026-03-25 22:31:24,416][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:31:24,417][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:31:30,867][__main__][INFO] - Number of regex retries in iteration 316: 0 [2026-03-25 22:31:30,868][__main__][INFO] - agents played in iteration 316 are Bob, Alice [2026-03-25 22:31:31,835][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:31:32,468][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:31:32,934][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:31:33,447][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:31:33,956][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:31:34,465][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:31:34,973][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:31:35,481][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:31:35,989][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:31:36,498][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:31:37,006][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:31:37,515][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:31:38,025][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:31:38,534][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:31:39,042][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:31:39,551][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:31:40,059][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:31:40,568][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:31:41,075][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:31:41,586][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:31:42,093][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:31:42,603][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:31:43,110][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:31:43,621][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:31:44,129][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:31:44,639][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:31:45,147][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:31:45,654][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:31:46,162][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:31:46,669][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:31:47,175][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:31:47,683][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:31:48,189][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:31:48,697][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:31:49,206][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:31:49,712][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:31:50,223][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:31:50,732][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:31:51,240][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:31:51,747][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:31:52,256][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:31:52,764][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:31:53,275][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:31:53,784][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:31:54,293][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:31:54,801][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:31:55,309][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:31:55,817][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:31:56,328][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:31:56,836][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:31:57,345][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:31:57,852][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:31:58,360][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:31:58,868][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:31:59,376][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:31:59,884][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:32:00,392][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:32:00,899][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:32:01,408][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:32:01,916][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:32:02,426][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:32:02,935][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:32:03,444][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:32:03,953][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:32:04,462][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:32:04,971][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:32:05,480][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:32:05,988][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:32:06,494][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:32:07,004][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:32:07,512][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:32:08,017][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:32:08,525][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:32:09,033][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:32:09,543][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:32:10,050][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:32:10,556][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:32:11,063][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:32:11,570][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:32:12,077][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:32:12,585][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:32:13,090][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:32:13,598][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:32:14,107][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:32:14,615][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:32:15,124][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:32:15,635][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:32:16,143][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:32:16,653][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:32:17,161][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:32:17,669][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:32:18,176][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:32:18,684][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:32:19,191][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:32:19,699][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:32:20,207][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:32:20,715][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:32:21,223][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:32:21,731][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:32:22,239][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:32:22,748][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:32:23,255][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:32:23,763][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:32:24,271][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:32:24,779][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:32:25,286][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:32:25,794][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:32:26,304][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:32:26,811][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:32:27,321][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:32:27,830][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:32:28,338][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:32:28,846][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:32:29,356][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:32:29,863][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:32:30,371][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:32:30,879][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:32:31,386][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:32:31,896][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:32:32,404][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:32:32,911][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:32:33,419][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:32:33,929][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:32:34,438][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:32:34,947][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:32:35,455][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:32:35,964][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:32:36,473][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:32:36,984][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:32:37,494][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 22:32:38,149][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 22:32:38,905][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:32:38,907][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:32:38,908][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:32:39,570][__main__][INFO] - Iteration 317 took 1m 15s (8.58% Gen, 90.53% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 40m 16s. Estimated total time: 62h 37m 42s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 15s, 500 more iterations: 10h 26m 17s. [2026-03-25 22:32:39,572][__main__][INFO] - Starting iteration 317. [2026-03-25 22:32:39,983][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:32:39,984][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:32:46,862][__main__][INFO] - Number of regex retries in iteration 317: 0 [2026-03-25 22:32:46,863][__main__][INFO] - agents played in iteration 317 are Bob, Alice [2026-03-25 22:32:47,836][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:32:48,458][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:32:48,921][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:32:49,433][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:32:49,942][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:32:50,449][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:32:50,956][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:32:51,462][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:32:51,969][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:32:52,476][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:32:52,987][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:32:53,494][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:32:54,004][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:32:54,512][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:32:55,020][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:32:55,529][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:32:56,036][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:32:56,545][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:32:57,056][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:32:57,566][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:32:58,076][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:32:58,586][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:32:59,095][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:32:59,605][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:33:00,114][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:33:00,625][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:33:01,134][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:33:01,643][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:33:02,152][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:33:02,660][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:33:03,169][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:33:03,678][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:33:04,186][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:33:04,693][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:33:05,203][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:33:05,713][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:33:06,222][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:33:06,733][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:33:07,243][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:33:07,753][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:33:08,263][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:33:08,772][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:33:09,280][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:33:09,788][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:33:10,296][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:33:10,805][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:33:11,313][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:33:11,822][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:33:12,331][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:33:12,839][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:33:13,348][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:33:13,857][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:33:14,366][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:33:14,874][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:33:15,382][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:33:15,889][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:33:16,398][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:33:16,906][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:33:17,414][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:33:17,923][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:33:18,430][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:33:18,939][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:33:19,447][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:33:19,955][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:33:20,463][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:33:20,972][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:33:21,479][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:33:21,986][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:33:22,493][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:33:23,001][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:33:23,509][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:33:24,015][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:33:24,523][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:33:25,030][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:33:25,538][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:33:26,046][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:33:26,554][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:33:27,062][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:33:27,569][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:33:28,077][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:33:28,584][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:33:29,091][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:33:29,601][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:33:30,110][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:33:30,619][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:33:31,129][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:33:31,638][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:33:32,147][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:33:32,656][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:33:33,165][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:33:33,673][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:33:34,182][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:33:34,690][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:33:35,199][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:33:35,706][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:33:36,214][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:33:36,723][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:33:37,231][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:33:37,742][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:33:38,250][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:33:38,758][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:33:39,269][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:33:39,777][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:33:40,286][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:33:40,794][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:33:41,303][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:33:41,811][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:33:42,320][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:33:42,828][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:33:43,335][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:33:43,844][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:33:44,352][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:33:44,860][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:33:45,368][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:33:45,875][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:33:46,383][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:33:46,891][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:33:47,398][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:33:47,907][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:33:48,415][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:33:48,924][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:33:49,433][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:33:49,943][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:33:50,451][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:33:50,958][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:33:51,466][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:33:51,975][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:33:52,483][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:33:52,990][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:33:53,499][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 22:33:54,153][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:05 [2026-03-25 22:33:54,912][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:33:54,915][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:33:54,916][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:33:55,774][__main__][INFO] - Iteration 318 took 1m 15s (9.08% Gen, 89.79% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 10m 54s. Estimated total time: 63h 9m 36s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 19s, 500 more iterations: 10h 31m 36s. [2026-03-25 22:33:55,777][__main__][INFO] - Starting iteration 318. [2026-03-25 22:33:56,182][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:33:56,183][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:34:02,873][__main__][INFO] - Number of regex retries in iteration 318: 0 [2026-03-25 22:34:02,874][__main__][INFO] - agents played in iteration 318 are Bob, Alice [2026-03-25 22:34:03,836][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:34:04,468][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:34:04,932][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:34:05,446][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:34:05,955][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:34:06,463][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:34:06,972][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:34:07,480][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:34:07,989][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:34:08,498][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:34:09,009][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:34:09,518][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:34:10,027][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:34:10,535][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:34:11,043][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:34:11,552][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:34:12,061][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:34:12,569][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:34:13,077][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:34:13,587][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:34:14,096][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:34:14,605][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:34:15,114][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:34:15,624][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:34:16,133][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:34:16,642][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:34:17,150][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:34:17,659][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:34:18,166][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:34:18,675][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:34:19,183][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:34:19,691][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:34:20,199][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:34:20,707][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:34:21,216][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:34:21,725][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:34:22,234][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:34:22,743][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:34:23,252][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:34:23,760][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:34:24,268][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:34:24,776][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:34:25,285][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:34:25,793][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:34:26,301][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:34:26,809][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:34:27,317][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:34:27,825][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:34:28,333][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:34:28,843][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:34:29,352][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:34:29,861][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:34:30,370][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:34:30,879][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:34:31,387][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:34:31,895][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:34:32,404][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:34:32,912][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:34:33,423][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:34:33,933][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:34:34,444][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:34:34,952][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:34:35,461][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:34:35,970][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:34:36,479][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:34:36,988][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:34:37,496][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:34:38,003][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:34:38,511][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:34:39,020][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:34:39,527][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:34:40,035][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:34:40,543][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:34:41,052][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:34:41,561][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:34:42,070][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:34:42,578][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:34:43,086][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:34:43,594][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:34:44,105][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:34:44,614][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:34:45,123][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:34:45,632][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:34:46,142][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:34:46,652][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:34:47,162][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:34:47,670][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:34:48,178][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:34:48,687][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:34:49,195][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:34:49,705][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:34:50,214][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:34:50,723][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:34:51,232][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:34:51,742][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:34:52,250][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:34:52,758][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:34:53,267][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:34:53,775][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:34:54,283][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:34:54,792][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:34:55,300][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:34:55,808][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:34:56,317][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:34:56,826][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:34:57,335][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:34:57,844][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:34:58,354][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:34:58,861][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:34:59,370][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:34:59,878][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:35:00,386][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:35:00,893][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:35:01,402][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:35:01,910][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:35:02,418][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:35:02,929][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:35:03,437][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:35:03,946][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:35:04,454][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:35:04,964][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:35:05,472][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:35:05,981][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:35:06,489][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:35:06,998][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:35:07,507][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:35:08,014][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:35:08,523][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:35:09,033][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:35:09,542][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21738 tokens. [2026-03-25 22:35:10,204][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 22:35:10,962][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:35:10,964][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:35:10,966][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:35:11,710][__main__][INFO] - Iteration 319 took 1m 15s (8.86% Gen, 90.15% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 56m 29s. Estimated total time: 62h 56m 28s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 52s, 500 more iterations: 10h 29m 24s. [2026-03-25 22:35:11,712][__main__][INFO] - Starting iteration 319. [2026-03-25 22:35:12,117][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:35:12,118][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:35:18,660][__main__][INFO] - Number of regex retries in iteration 319: 0 [2026-03-25 22:35:18,661][__main__][INFO] - agents played in iteration 319 are Bob, Alice [2026-03-25 22:35:19,631][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:35:20,262][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:35:20,728][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:35:21,241][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:35:21,749][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:35:22,258][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:35:22,766][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:35:23,276][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:35:23,783][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:35:24,292][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:35:24,803][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:35:25,312][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:35:25,824][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:35:26,334][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:35:26,844][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:35:27,354][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:35:27,871][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:35:28,382][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:35:28,896][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:35:29,411][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:35:29,920][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:35:30,430][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:35:30,943][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:35:31,453][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:35:31,964][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:35:32,474][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:35:32,985][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:35:33,495][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:35:34,005][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:35:34,515][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:35:35,025][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:35:35,535][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:35:36,046][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:35:36,557][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:35:37,067][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:35:37,574][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:35:38,084][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:35:38,593][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:35:39,103][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:35:39,612][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:35:40,122][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:35:40,633][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:35:41,143][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:35:41,653][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:35:42,162][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:35:42,671][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:35:43,184][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:35:43,691][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:35:44,200][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:35:44,709][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:35:45,218][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:35:45,727][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:35:46,235][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:35:46,744][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:35:47,260][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:35:47,769][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:35:48,288][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:35:48,798][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:35:49,308][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:35:49,818][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:35:50,330][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:35:50,840][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:35:51,351][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:35:51,861][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:35:52,372][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:35:52,882][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:35:53,390][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:35:53,899][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:35:54,408][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:35:54,917][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:35:55,426][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:35:55,935][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:35:56,444][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:35:56,953][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:35:57,463][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:35:57,972][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:35:58,481][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:35:58,991][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:35:59,501][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:36:00,011][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:36:00,520][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:36:01,030][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:36:01,539][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:36:02,048][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:36:02,556][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:36:03,065][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:36:03,574][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:36:04,084][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:36:04,593][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:36:05,103][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:36:05,613][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:36:06,122][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:36:06,631][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:36:07,141][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:36:07,650][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:36:08,158][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:36:08,668][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:36:09,177][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:36:09,686][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:36:10,194][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:36:10,704][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:36:11,212][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:36:11,721][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:36:12,230][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:36:12,738][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:36:13,247][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:36:13,756][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:36:14,265][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:36:14,775][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:36:15,285][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:36:15,794][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:36:16,304][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:36:16,814][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:36:17,325][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:36:17,834][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:36:18,343][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:36:18,852][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:36:19,360][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:36:19,868][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:36:20,376][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:36:20,885][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:36:21,393][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:36:21,903][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:36:22,413][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:36:22,923][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:36:23,432][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:36:23,942][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:36:24,451][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:36:24,960][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:36:25,470][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 22:36:26,136][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 22:36:26,898][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:36:26,900][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:36:26,902][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:36:27,755][__main__][INFO] - Iteration 320 took 1m 15s (8.65% Gen, 90.22% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 0m 40s. Estimated total time: 63h 1m 54s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 3s, 500 more iterations: 10h 30m 19s. [2026-03-25 22:36:27,757][__main__][INFO] - Starting iteration 320. [2026-03-25 22:36:28,157][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:36:28,158][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:36:34,631][__main__][INFO] - Number of regex retries in iteration 320: 0 [2026-03-25 22:36:34,632][__main__][INFO] - agents played in iteration 320 are Bob, Alice [2026-03-25 22:36:35,583][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:36:36,207][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:36:36,672][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:36:37,185][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:36:37,701][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:36:38,210][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:36:38,720][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:36:39,229][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:36:39,740][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:36:40,262][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:36:40,772][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:36:41,281][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:36:41,791][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:36:42,299][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:36:42,811][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:36:43,321][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:36:43,830][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:36:44,339][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:36:44,851][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:36:45,362][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:36:45,871][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:36:46,380][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:36:46,889][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:36:47,398][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:36:47,907][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:36:48,416][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:36:48,924][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:36:49,430][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:36:49,938][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:36:50,445][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:36:50,951][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:36:51,458][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:36:51,964][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:36:52,468][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:36:52,976][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:36:53,485][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:36:53,994][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:36:54,503][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:36:55,012][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:36:55,521][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:36:56,029][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:36:56,537][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:36:57,046][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:36:57,554][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:36:58,064][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:36:58,574][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:36:59,084][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:36:59,592][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:37:00,101][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:37:00,610][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:37:01,118][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:37:01,627][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:37:02,136][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:37:02,645][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:37:03,155][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:37:03,664][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:37:04,173][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:37:04,682][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:37:05,190][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:37:05,699][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:37:06,209][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:37:06,718][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:37:07,228][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:37:07,737][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:37:08,245][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:37:08,753][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:37:09,263][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:37:09,772][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:37:10,281][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:37:10,789][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:37:11,297][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:37:11,806][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:37:12,314][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:37:12,824][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:37:13,332][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:37:13,841][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:37:14,349][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:37:14,857][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:37:15,365][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:37:15,872][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:37:16,381][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:37:16,888][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:37:17,396][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:37:17,905][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:37:18,415][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:37:18,925][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:37:19,434][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:37:19,944][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:37:20,454][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:37:20,963][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:37:21,472][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:37:21,980][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:37:22,487][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:37:22,993][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:37:23,503][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:37:24,011][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:37:24,519][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:37:25,027][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:37:25,534][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:37:26,042][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:37:26,549][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:37:27,057][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:37:27,564][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:37:28,072][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:37:28,579][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:37:29,087][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:37:29,596][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:37:30,103][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:37:30,612][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:37:31,121][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:37:31,630][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:37:32,139][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:37:32,647][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:37:33,156][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:37:33,666][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:37:34,175][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:37:34,683][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:37:35,193][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:37:35,701][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:37:36,210][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:37:36,720][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:37:37,230][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:37:37,738][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:37:38,249][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:37:38,760][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:37:39,270][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:37:39,780][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:37:40,290][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:37:40,800][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:37:41,311][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 22:37:41,973][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 22:37:42,741][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:37:42,743][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:37:42,745][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:37:43,492][__main__][INFO] - Iteration 321 took 1m 15s (8.59% Gen, 90.41% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 44m 18s. Estimated total time: 62h 46m 48s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 33s, 500 more iterations: 10h 27m 48s. [2026-03-25 22:37:43,494][__main__][INFO] - Starting iteration 321. [2026-03-25 22:37:43,895][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:37:43,895][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:37:48,281][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:37:50,777][__main__][INFO] - Number of regex retries in iteration 321: 1 [2026-03-25 22:37:50,778][__main__][INFO] - agents played in iteration 321 are Bob, Alice [2026-03-25 22:37:52,035][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:37:52,664][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:37:53,124][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:37:53,636][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:37:54,142][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:37:54,649][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:37:55,157][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:37:55,663][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:37:56,169][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:37:56,676][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:37:57,185][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:37:57,692][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:37:58,199][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:37:58,706][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:37:59,214][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:37:59,721][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:38:00,230][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:38:00,737][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:38:01,247][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:38:01,756][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:38:02,265][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:38:02,774][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:38:03,281][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:38:03,790][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:38:04,298][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:38:04,807][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:38:05,317][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:38:05,826][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:38:06,334][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:38:06,843][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:38:07,351][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:38:07,860][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:38:08,368][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:38:08,876][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:38:09,381][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:38:09,887][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:38:10,394][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:38:10,900][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:38:11,406][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:38:11,912][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:38:12,418][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:38:12,925][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:38:13,433][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:38:13,940][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:38:14,447][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:38:14,955][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:38:15,461][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:38:15,969][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:38:16,477][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:38:16,985][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:38:17,493][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:38:18,002][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:38:18,511][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:38:19,021][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:38:19,531][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:38:20,039][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:38:20,548][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:38:21,057][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:38:21,567][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:38:22,075][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:38:22,585][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:38:23,094][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:38:23,604][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:38:24,113][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:38:24,622][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:38:25,132][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:38:25,638][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:38:26,145][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:38:26,654][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:38:27,160][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:38:27,667][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:38:28,173][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:38:28,679][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:38:29,185][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:38:29,693][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:38:30,201][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:38:30,708][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:38:31,215][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:38:31,724][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:38:32,230][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:38:32,739][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:38:33,246][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:38:33,754][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:38:34,261][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:38:34,767][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:38:35,276][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:38:35,784][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:38:36,291][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:38:36,799][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:38:37,309][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:38:37,818][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:38:38,328][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:38:38,837][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:38:39,346][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:38:39,855][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:38:40,363][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:38:40,873][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:38:41,381][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:38:41,886][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:38:42,393][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:38:42,899][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:38:43,406][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:38:43,912][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:38:44,419][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:38:44,926][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:38:45,433][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:38:45,942][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:38:46,450][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:38:46,957][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:38:47,465][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:38:47,972][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:38:48,482][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:38:48,989][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:38:49,497][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:38:50,006][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:38:50,516][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:38:51,025][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:38:51,534][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:38:52,044][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:38:52,553][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:38:53,061][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:38:53,570][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:38:54,078][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:38:54,587][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:38:55,096][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:38:55,605][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:38:56,114][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:38:56,623][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:38:57,132][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:38:57,644][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 22:38:58,312][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-25 22:38:59,070][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:38:59,072][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:38:59,074][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:38:59,764][__main__][INFO] - Iteration 322 took 1m 15s (9.07% Gen, 90.02% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 9m 44s. Estimated total time: 63h 13m 31s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 27s, 500 more iterations: 10h 32m 15s. [2026-03-25 22:38:59,767][__main__][INFO] - Starting iteration 322. [2026-03-25 22:39:00,171][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:39:00,172][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:39:00,807][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:39:03,827][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:39:07,448][__main__][INFO] - Number of regex retries in iteration 322: 2 [2026-03-25 22:39:07,449][__main__][INFO] - agents played in iteration 322 are Bob, Alice [2026-03-25 22:39:08,413][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:39:09,051][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:39:09,518][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:39:10,032][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:39:10,542][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:39:11,051][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:39:11,558][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:39:12,068][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:39:12,576][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:39:13,085][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:39:13,593][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:39:14,106][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:39:14,615][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:39:15,126][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:39:15,636][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:39:16,145][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:39:16,655][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:39:17,165][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:39:17,673][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:39:18,181][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:39:18,700][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:39:19,210][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:39:19,719][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:39:20,227][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:39:20,735][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:39:21,244][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:39:21,755][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:39:22,266][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:39:22,776][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:39:23,286][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:39:23,798][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:39:24,307][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:39:24,818][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:39:25,328][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:39:25,836][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:39:26,346][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:39:26,855][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:39:27,364][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:39:27,872][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:39:28,382][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:39:28,891][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:39:29,399][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:39:29,907][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:39:30,415][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:39:30,923][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:39:31,432][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:39:31,942][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:39:32,451][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:39:32,958][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:39:33,468][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:39:33,975][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:39:34,483][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:39:34,991][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:39:35,498][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:39:36,007][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:39:36,515][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:39:37,023][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:39:37,531][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:39:38,039][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:39:38,546][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:39:39,054][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:39:39,563][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:39:40,071][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:39:40,579][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:39:41,086][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:39:41,594][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:39:42,103][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:39:42,612][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:39:43,121][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:39:43,630][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:39:44,139][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:39:44,648][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:39:45,156][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:39:45,665][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:39:46,174][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:39:46,683][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:39:47,191][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:39:47,700][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:39:48,209][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:39:48,717][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:39:49,225][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:39:49,734][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:39:50,242][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:39:50,750][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:39:51,259][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:39:51,766][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:39:52,273][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:39:52,780][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:39:53,287][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:39:53,794][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:39:54,302][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:39:54,811][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:39:55,320][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:39:55,829][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:39:56,338][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:39:56,847][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:39:57,356][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:39:57,865][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:39:58,373][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:39:58,882][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:39:59,391][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:39:59,900][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:40:00,409][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:40:00,917][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:40:01,426][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:40:01,935][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:40:02,443][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:40:02,951][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:40:03,460][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:40:03,968][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:40:04,475][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:40:04,984][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:40:05,493][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:40:06,000][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:40:06,508][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:40:07,016][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:40:07,524][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:40:08,032][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:40:08,539][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:40:09,047][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:40:09,555][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:40:10,062][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:40:10,569][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:40:11,078][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:40:11,586][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:40:12,094][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:40:12,599][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:40:13,106][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:40:13,616][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:40:14,124][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21726 tokens. [2026-03-25 22:40:14,789][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-25 22:40:15,547][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:40:15,549][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:40:15,551][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:40:16,298][__main__][INFO] - Iteration 323 took 1m 16s (9.56% Gen, 89.46% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 56h 21m 18s. Estimated total time: 63h 26m 21s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 52s, 500 more iterations: 10h 34m 23s. [2026-03-25 22:40:16,300][__main__][INFO] - Starting iteration 323. [2026-03-25 22:40:16,701][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:40:16,702][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:40:18,526][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:40:24,072][__main__][INFO] - Number of regex retries in iteration 323: 1 [2026-03-25 22:40:24,073][__main__][INFO] - agents played in iteration 323 are Bob, Alice [2026-03-25 22:40:25,045][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:40:25,674][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:40:26,136][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:40:26,645][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:40:27,150][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:40:27,654][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:40:28,160][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:40:28,666][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:40:29,171][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:40:29,675][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:40:30,188][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:40:30,697][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:40:31,208][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:40:31,717][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:40:32,227][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:40:32,737][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:40:33,247][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:40:33,758][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:40:34,268][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:40:34,777][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:40:35,287][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:40:35,796][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:40:36,304][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:40:36,812][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:40:37,324][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:40:37,835][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:40:38,344][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:40:38,854][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:40:39,364][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:40:39,873][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:40:40,382][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:40:40,892][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:40:41,402][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:40:41,911][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:40:42,422][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:40:42,931][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:40:43,441][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:40:43,950][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:40:44,459][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:40:44,968][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:40:45,476][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:40:45,986][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:40:46,495][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:40:47,004][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:40:47,512][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:40:48,021][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:40:48,529][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:40:49,037][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:40:49,545][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:40:50,054][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:40:50,564][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:40:51,073][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:40:51,581][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:40:52,090][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:40:52,598][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:40:53,106][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:40:53,615][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:40:54,126][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:40:54,635][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:40:55,143][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:40:55,652][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:40:56,162][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:40:56,671][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:40:57,179][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:40:57,688][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:40:58,196][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:40:58,701][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:40:59,206][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:40:59,710][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:41:00,215][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:41:00,720][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:41:01,225][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:41:01,729][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:41:02,233][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:41:02,743][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:41:03,253][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:41:03,764][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:41:04,274][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:41:04,784][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:41:05,294][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:41:05,804][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:41:06,313][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:41:06,822][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:41:07,332][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:41:07,844][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:41:08,354][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:41:08,864][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:41:09,374][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:41:09,885][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:41:10,395][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:41:10,905][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:41:11,414][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:41:11,924][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:41:12,433][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:41:12,942][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:41:13,452][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:41:13,962][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:41:14,471][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:41:14,982][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:41:15,491][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:41:16,000][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:41:16,509][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:41:17,019][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:41:17,528][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:41:18,038][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:41:18,547][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:41:19,056][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:41:19,564][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:41:20,072][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:41:20,582][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:41:21,090][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:41:21,598][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:41:22,107][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:41:22,615][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:41:23,125][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:41:23,634][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:41:24,144][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:41:24,652][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:41:25,159][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:41:25,665][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:41:26,175][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:41:26,684][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:41:27,194][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:41:27,705][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:41:28,215][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:41:28,725][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:41:29,235][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:41:29,745][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:41:30,254][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:41:30,764][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 22:41:31,427][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.39%, ΔTime: 00:01:05 [2026-03-25 22:41:32,189][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:41:32,191][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:41:32,193][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:41:32,861][__main__][INFO] - Iteration 324 took 1m 16s (9.68% Gen, 89.44% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 56h 21m 41s. Estimated total time: 63h 28m 0s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 56s, 500 more iterations: 10h 34m 40s. [2026-03-25 22:41:32,863][__main__][INFO] - Starting iteration 324. [2026-03-25 22:41:33,265][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:41:33,265][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:41:33,902][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:41:39,581][__main__][INFO] - Number of regex retries in iteration 324: 1 [2026-03-25 22:41:39,581][__main__][INFO] - agents played in iteration 324 are Bob, Alice [2026-03-25 22:41:40,547][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:41:41,465][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:41:41,930][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:41:42,444][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:41:42,953][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:41:43,461][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:41:43,970][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:41:44,479][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:41:44,988][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:41:45,496][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:41:46,005][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:41:46,514][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:41:47,023][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:41:47,533][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:41:48,043][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:41:48,553][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:41:49,062][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:41:49,572][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:41:50,081][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:41:50,591][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:41:51,100][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:41:51,610][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:41:52,119][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:41:52,629][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:41:53,138][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:41:53,648][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:41:54,158][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:41:54,668][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:41:55,177][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:41:55,686][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:41:56,195][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:41:56,705][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:41:57,216][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:41:57,726][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:41:58,236][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:41:58,744][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:41:59,252][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:41:59,759][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:42:00,266][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:42:00,773][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:42:01,280][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:42:01,788][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:42:02,297][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:42:02,805][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:42:03,313][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:42:03,822][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:42:04,331][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:42:04,840][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:42:05,349][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:42:05,859][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:42:06,368][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:42:06,876][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:42:07,386][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:42:07,893][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:42:08,403][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:42:08,912][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:42:09,420][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:42:09,929][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:42:10,438][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:42:10,944][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:42:11,453][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:42:11,961][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:42:12,469][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:42:12,976][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:42:13,483][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:42:13,990][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:42:14,499][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:42:15,007][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:42:15,515][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:42:16,026][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:42:16,535][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:42:17,044][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:42:17,553][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:42:18,063][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:42:18,570][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:42:19,080][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:42:19,588][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:42:20,097][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:42:20,605][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:42:21,114][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:42:21,625][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:42:22,135][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:42:22,640][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:42:23,149][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:42:23,657][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:42:24,165][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:42:24,673][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:42:25,180][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:42:25,688][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:42:26,197][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:42:26,706][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:42:27,214][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:42:27,724][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:42:28,232][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:42:28,741][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:42:29,248][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:42:29,756][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:42:30,264][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:42:30,771][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:42:31,279][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:42:31,786][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:42:32,294][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:42:32,801][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:42:33,310][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:42:33,818][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:42:34,326][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:42:34,835][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:42:35,344][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:42:35,853][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:42:36,360][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:42:36,869][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:42:37,377][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:42:37,885][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:42:38,393][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:42:38,902][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:42:39,410][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:42:39,919][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:42:40,428][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:42:40,936][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:42:41,446][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:42:41,955][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:42:42,463][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:42:42,971][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:42:43,478][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:42:43,985][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:42:44,492][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:42:45,002][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:42:45,510][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:42:46,019][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:42:46,527][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21747 tokens. [2026-03-25 22:42:47,187][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.16%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-25 22:42:47,946][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:42:47,948][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:42:47,950][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:42:48,801][__main__][INFO] - Iteration 325 took 1m 15s (8.36% Gen, 90.51% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 49m 14s. Estimated total time: 62h 56m 50s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 53s, 500 more iterations: 10h 29m 28s. [2026-03-25 22:42:48,803][__main__][INFO] - Starting iteration 325. [2026-03-25 22:42:49,203][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:42:49,203][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:42:56,786][__main__][INFO] - Number of regex retries in iteration 325: 0 [2026-03-25 22:42:56,787][__main__][INFO] - agents played in iteration 325 are Bob, Alice [2026-03-25 22:42:57,756][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:42:58,389][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:42:58,853][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:42:59,366][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:42:59,874][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:43:00,383][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:43:00,890][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:43:01,398][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:43:01,905][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:43:02,413][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:43:02,927][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:43:03,436][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:43:03,944][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:43:04,454][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:43:04,963][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:43:05,473][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:43:05,981][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:43:06,490][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:43:06,998][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:43:07,506][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:43:08,015][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:43:08,524][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:43:09,033][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:43:09,542][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:43:10,050][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:43:10,558][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:43:11,067][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:43:11,575][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:43:12,084][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:43:12,592][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:43:13,101][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:43:13,609][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:43:14,118][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:43:14,626][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:43:15,135][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:43:15,644][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:43:16,153][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:43:16,662][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:43:17,171][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:43:17,679][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:43:18,187][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:43:18,696][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:43:19,208][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:43:19,717][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:43:20,226][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:43:20,736][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:43:21,244][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:43:21,754][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:43:22,263][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:43:22,772][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:43:23,280][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:43:23,789][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:43:24,298][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:43:24,808][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:43:25,317][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:43:25,826][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:43:26,335][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:43:26,845][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:43:27,354][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:43:27,863][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:43:28,372][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:43:28,880][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:43:29,390][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:43:29,899][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:43:30,407][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:43:30,915][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:43:31,424][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:43:31,932][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:43:32,439][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:43:32,946][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:43:33,453][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:43:33,960][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:43:34,467][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:43:34,973][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:43:35,483][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:43:35,991][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:43:36,499][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:43:37,007][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:43:37,515][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:43:38,024][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:43:38,533][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:43:39,044][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:43:39,552][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:43:40,059][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:43:40,567][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:43:41,075][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:43:41,582][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:43:42,090][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:43:42,597][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:43:43,107][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:43:43,616][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:43:44,126][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:43:44,635][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:43:45,144][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:43:45,654][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:43:46,164][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:43:46,673][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:43:47,184][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:43:47,693][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:43:48,203][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:43:48,712][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:43:49,221][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:43:49,730][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:43:50,238][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:43:50,747][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:43:51,255][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:43:51,764][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:43:52,273][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:43:52,782][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:43:53,290][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:43:53,797][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:43:54,307][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:43:54,816][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:43:55,325][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:43:55,834][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:43:56,343][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:43:56,852][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:43:57,360][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:43:57,870][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:43:58,378][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:43:58,887][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:43:59,395][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:43:59,905][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:44:00,414][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:44:00,923][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:44:01,432][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:44:01,942][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:44:02,450][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:44:02,958][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:44:03,467][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-25 22:44:04,128][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 22:44:04,882][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:44:04,884][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:44:04,885][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:44:05,555][__main__][INFO] - Iteration 326 took 1m 16s (9.93% Gen, 89.19% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 56h 28m 45s. Estimated total time: 63h 37m 37s. Time estimates for 10 more iterations: 12m 43s, 100 more iterations: 2h 7m 15s, 500 more iterations: 10h 36m 16s. [2026-03-25 22:44:05,557][__main__][INFO] - Starting iteration 326. [2026-03-25 22:44:05,962][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:44:05,963][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:44:10,626][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:44:12,925][__main__][INFO] - Number of regex retries in iteration 326: 1 [2026-03-25 22:44:12,926][__main__][INFO] - agents played in iteration 326 are Bob, Alice [2026-03-25 22:44:13,892][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:44:14,521][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:44:14,986][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:44:15,500][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:44:16,007][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:44:16,516][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:44:17,025][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:44:17,534][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:44:18,043][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:44:18,552][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:44:19,058][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:44:19,566][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:44:20,073][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:44:20,580][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:44:21,087][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:44:21,594][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:44:22,103][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:44:22,610][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:44:23,119][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:44:23,628][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:44:24,136][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:44:24,645][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:44:25,154][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:44:25,663][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:44:26,171][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:44:26,680][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:44:27,187][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:44:27,695][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:44:28,202][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:44:28,710][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:44:29,218][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:44:29,727][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:44:30,235][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:44:30,743][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:44:31,250][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:44:31,757][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:44:32,265][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:44:32,772][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:44:33,278][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:44:33,786][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:44:34,293][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:44:34,800][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:44:35,308][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:44:35,816][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:44:36,324][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:44:36,833][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:44:37,340][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:44:37,847][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:44:38,355][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:44:38,863][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:44:39,372][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:44:39,881][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:44:40,389][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:44:40,899][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:44:41,406][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:44:41,915][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:44:42,425][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:44:42,933][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:44:43,447][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:44:43,959][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:44:44,469][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:44:44,981][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:44:45,493][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:44:46,004][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:44:46,516][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:44:47,027][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:44:47,535][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:44:48,045][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:44:48,554][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:44:49,064][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:44:49,573][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:44:50,081][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:44:50,591][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:44:51,100][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:44:51,607][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:44:52,114][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:44:52,623][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:44:53,130][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:44:53,636][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:44:54,144][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:44:54,651][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:44:55,159][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:44:55,666][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:44:56,174][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:44:56,684][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:44:57,192][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:44:57,701][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:44:58,210][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:44:58,719][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:44:59,227][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:44:59,732][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:45:00,240][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:45:00,748][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:45:01,256][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:45:01,764][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:45:02,272][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:45:02,779][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:45:03,287][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:45:03,793][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:45:04,301][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:45:04,809][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:45:05,316][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:45:05,826][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:45:06,334][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:45:06,843][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:45:07,350][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:45:07,858][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:45:08,366][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:45:08,874][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:45:09,382][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:45:09,889][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:45:10,396][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:45:10,904][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:45:11,412][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:45:11,920][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:45:12,429][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:45:12,939][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:45:13,447][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:45:13,955][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:45:14,464][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:45:14,972][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:45:15,481][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:45:15,992][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:45:16,504][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:45:17,016][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:45:17,528][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:45:18,039][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:45:18,551][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:45:19,062][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:45:19,572][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21747 tokens. [2026-03-25 22:45:20,230][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.32%, Current % of VRAM taken: 60.68%, Block Peak % of device VRAM: 62.53%, ΔTime: 00:01:05 [2026-03-25 22:45:20,982][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:45:20,984][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:45:20,986][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:45:21,872][__main__][INFO] - Iteration 327 took 1m 15s (9.17% Gen, 89.66% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 5m 20s. Estimated total time: 63h 15m 29s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 30s, 500 more iterations: 10h 32m 34s. [2026-03-25 22:45:21,874][__main__][INFO] - Starting iteration 327. [2026-03-25 22:45:22,277][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:45:22,277][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:45:24,638][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:45:29,382][__main__][INFO] - Number of regex retries in iteration 327: 1 [2026-03-25 22:45:29,383][__main__][INFO] - agents played in iteration 327 are Bob, Alice [2026-03-25 22:45:30,342][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:45:30,973][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:45:31,440][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:45:31,954][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:45:32,465][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:45:32,973][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:45:33,482][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:45:33,991][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:45:34,499][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:45:35,008][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:45:35,514][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:45:36,022][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:45:36,529][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:45:37,036][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:45:37,543][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:45:38,049][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:45:38,556][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:45:39,062][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:45:39,570][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:45:40,078][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:45:40,587][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:45:41,095][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:45:41,604][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:45:42,113][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:45:42,622][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:45:43,131][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:45:43,640][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:45:44,147][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:45:44,655][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:45:45,160][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:45:45,665][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:45:46,172][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:45:46,681][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:45:47,189][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:45:47,696][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:45:48,204][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:45:48,711][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:45:49,218][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:45:49,726][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:45:50,235][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:45:50,744][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:45:51,252][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:45:51,760][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:45:52,269][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:45:52,778][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:45:53,286][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:45:53,795][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:45:54,304][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:45:54,812][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:45:55,321][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:45:55,828][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:45:56,335][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:45:56,841][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:45:57,349][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:45:57,855][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:45:58,361][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:45:58,867][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:45:59,373][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:45:59,882][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:46:00,387][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:46:00,893][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:46:01,400][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:46:01,905][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:46:02,412][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:46:02,919][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:46:03,426][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:46:03,935][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:46:04,444][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:46:04,951][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:46:05,459][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:46:05,967][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:46:06,475][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:46:06,984][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:46:07,492][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:46:07,999][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:46:08,505][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:46:09,012][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:46:09,518][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:46:10,025][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:46:10,533][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:46:11,040][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:46:11,547][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:46:12,052][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:46:12,563][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:46:13,073][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:46:13,582][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:46:14,090][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:46:14,599][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:46:15,107][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:46:15,615][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:46:16,125][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:46:16,633][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:46:17,141][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:46:17,649][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:46:18,157][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:46:18,664][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:46:19,171][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:46:19,678][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:46:20,186][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:46:20,693][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:46:21,200][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:46:21,706][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:46:22,213][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:46:22,722][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:46:23,229][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:46:23,735][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:46:24,244][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:46:24,753][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:46:25,261][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:46:25,769][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:46:26,278][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:46:26,786][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:46:27,295][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:46:27,803][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:46:28,311][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:46:28,819][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:46:29,327][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:46:29,835][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:46:30,343][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:46:30,850][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:46:31,357][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:46:31,865][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:46:32,371][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:46:32,878][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:46:33,385][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:46:33,891][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:46:34,397][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:46:34,904][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:46:35,411][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:46:35,916][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-25 22:46:36,590][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-25 22:46:37,343][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:46:37,345][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:46:37,347][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:46:38,015][__main__][INFO] - Iteration 328 took 1m 15s (9.38% Gen, 89.73% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 55h 55m 33s. Estimated total time: 63h 6m 58s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 13s, 500 more iterations: 10h 31m 9s. [2026-03-25 22:46:38,017][__main__][INFO] - Starting iteration 328. [2026-03-25 22:46:38,430][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:46:38,431][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:46:41,181][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:46:45,823][__main__][INFO] - Number of regex retries in iteration 328: 1 [2026-03-25 22:46:45,823][__main__][INFO] - agents played in iteration 328 are Bob, Alice [2026-03-25 22:46:46,775][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:46:47,414][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:46:47,878][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:46:48,390][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:46:48,899][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:46:49,408][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:46:49,916][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:46:50,426][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:46:50,936][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:46:51,444][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:46:51,953][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:46:52,462][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:46:52,970][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:46:53,478][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:46:53,986][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:46:54,494][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:46:55,002][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:46:55,519][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:46:56,029][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:46:56,539][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:46:57,048][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:46:57,558][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:46:58,067][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:46:58,576][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:46:59,084][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:46:59,593][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:47:00,105][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:47:00,615][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:47:01,126][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:47:01,637][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:47:02,146][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:47:02,655][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:47:03,165][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:47:03,675][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:47:04,184][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:47:04,693][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:47:05,203][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:47:05,712][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:47:06,219][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:47:06,727][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:47:07,236][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:47:07,745][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:47:08,253][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:47:08,763][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:47:09,273][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:47:09,782][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:47:10,291][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:47:10,801][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:47:11,310][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:47:11,818][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:47:12,327][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:47:12,835][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:47:13,343][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:47:13,852][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:47:14,358][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:47:14,866][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:47:15,373][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:47:15,881][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:47:16,391][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:47:16,901][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:47:17,410][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:47:17,919][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:47:18,430][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:47:18,940][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:47:19,449][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:47:19,959][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:47:20,467][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:47:20,975][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:47:21,482][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:47:21,990][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:47:22,499][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:47:23,005][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:47:23,513][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:47:24,024][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:47:24,531][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:47:25,039][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:47:25,547][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:47:26,068][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:47:26,575][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:47:27,083][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:47:27,591][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:47:28,099][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:47:28,607][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:47:29,114][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:47:29,623][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:47:30,132][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:47:30,640][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:47:31,148][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:47:31,657][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:47:32,165][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:47:32,673][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:47:33,181][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:47:33,690][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:47:34,199][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:47:34,708][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:47:35,216][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:47:35,725][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:47:36,234][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:47:36,742][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:47:37,249][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:47:37,757][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:47:38,265][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:47:38,772][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:47:39,281][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:47:39,789][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:47:40,297][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:47:40,807][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:47:41,315][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:47:41,824][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:47:42,334][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:47:42,842][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:47:43,350][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:47:43,859][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:47:44,368][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:47:44,875][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:47:45,382][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:47:45,889][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:47:46,397][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:47:46,904][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:47:47,411][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:47:47,919][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:47:48,427][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:47:48,936][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:47:49,446][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:47:49,956][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:47:50,465][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:47:50,974][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:47:51,485][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:47:51,994][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:47:52,505][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 22:47:53,183][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.65%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 22:47:53,939][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:47:53,941][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:47:53,943][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:47:54,691][__main__][INFO] - Iteration 329 took 1m 16s (9.69% Gen, 89.32% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 56h 20m 25s. Estimated total time: 63h 33m 6s. Time estimates for 10 more iterations: 12m 42s, 100 more iterations: 2h 7m 6s, 500 more iterations: 10h 35m 31s. [2026-03-25 22:47:54,695][__main__][INFO] - Starting iteration 329. [2026-03-25 22:47:55,100][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:47:55,101][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:48:01,842][__main__][INFO] - Number of regex retries in iteration 329: 0 [2026-03-25 22:48:01,843][__main__][INFO] - agents played in iteration 329 are Bob, Alice [2026-03-25 22:48:02,805][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:48:03,426][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:48:03,890][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:48:04,405][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:48:04,913][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:48:05,423][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:48:05,932][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:48:06,442][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:48:06,952][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:48:07,461][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:48:07,968][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:48:08,475][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:48:08,982][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:48:09,489][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:48:09,995][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:48:10,504][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:48:11,012][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:48:11,519][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:48:12,030][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:48:12,539][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:48:13,048][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:48:13,557][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:48:14,066][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:48:14,575][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:48:15,084][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:48:15,598][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:48:16,110][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:48:16,620][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:48:17,129][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:48:17,639][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:48:18,148][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:48:18,657][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:48:19,166][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:48:19,675][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:48:20,196][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:48:20,706][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:48:21,215][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:48:21,725][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:48:22,235][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:48:22,745][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:48:23,254][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:48:23,763][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:48:24,272][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:48:24,784][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:48:25,293][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:48:25,802][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:48:26,311][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:48:26,821][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:48:27,330][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:48:27,840][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:48:28,347][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:48:28,856][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:48:29,365][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:48:29,874][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:48:30,384][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:48:30,893][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:48:31,401][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:48:31,910][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:48:32,420][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:48:32,929][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:48:33,438][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:48:33,947][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:48:34,455][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:48:34,964][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:48:35,474][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:48:35,985][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:48:36,494][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:48:37,003][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:48:37,513][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:48:38,024][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:48:38,533][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:48:39,043][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:48:39,553][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:48:40,063][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:48:40,571][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:48:41,078][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:48:41,587][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:48:42,095][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:48:42,604][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:48:43,111][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:48:43,620][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:48:44,128][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:48:44,637][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:48:45,146][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:48:45,655][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:48:46,165][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:48:46,674][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:48:47,184][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:48:47,694][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:48:48,203][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:48:48,712][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:48:49,220][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:48:49,728][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:48:50,236][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:48:50,746][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:48:51,254][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:48:51,763][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:48:52,271][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:48:52,778][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:48:53,287][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:48:53,795][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:48:54,305][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:48:54,813][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:48:55,322][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:48:55,831][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:48:56,338][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:48:56,848][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:48:57,357][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:48:57,865][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:48:58,373][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:48:58,882][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:48:59,390][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:48:59,898][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:49:00,408][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:49:00,916][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:49:01,425][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:49:01,933][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:49:02,444][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:49:02,953][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:49:03,462][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:49:03,970][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:49:04,479][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:49:04,988][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:49:05,497][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:49:06,005][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:49:06,514][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:49:07,025][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:49:07,534][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:49:08,045][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:49:08,556][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 22:49:09,219][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-25 22:49:09,995][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:49:09,997][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:49:09,999][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:49:10,714][__main__][INFO] - Iteration 330 took 1m 15s (8.92% Gen, 90.14% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 46m 45s. Estimated total time: 63h 0m 43s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 1s, 500 more iterations: 10h 30m 7s. [2026-03-25 22:49:10,716][__main__][INFO] - Starting iteration 330. [2026-03-25 22:49:11,119][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:49:11,119][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:49:14,149][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:49:18,678][__main__][INFO] - Number of regex retries in iteration 330: 1 [2026-03-25 22:49:18,679][__main__][INFO] - agents played in iteration 330 are Bob, Alice [2026-03-25 22:49:19,638][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:49:20,270][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:49:20,736][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:49:21,248][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:49:21,756][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:49:22,266][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:49:22,774][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:49:23,282][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:49:23,790][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:49:24,299][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:49:24,807][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:49:25,315][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:49:25,826][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:49:26,336][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:49:26,844][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:49:27,358][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:49:27,869][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:49:28,378][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:49:28,887][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:49:29,397][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:49:29,907][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:49:30,418][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:49:30,926][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:49:31,436][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:49:31,958][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:49:32,469][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:49:32,979][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:49:33,488][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:49:33,997][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:49:34,509][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:49:35,019][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:49:35,529][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:49:36,039][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:49:36,549][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:49:37,057][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:49:37,566][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:49:38,074][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:49:38,582][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:49:39,090][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:49:39,598][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:49:40,108][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:49:40,618][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:49:41,129][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:49:41,639][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:49:42,148][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:49:42,658][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:49:43,168][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:49:43,675][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:49:44,185][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:49:44,695][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:49:45,204][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:49:45,714][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:49:46,223][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:49:46,733][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:49:47,244][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:49:47,754][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:49:48,263][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:49:48,772][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:49:49,287][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:49:49,798][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:49:50,311][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:49:50,825][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:49:51,337][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:49:51,850][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:49:52,363][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:49:52,877][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:49:53,386][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:49:53,895][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:49:54,405][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:49:54,915][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:49:55,426][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:49:55,936][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:49:56,446][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:49:56,955][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:49:57,466][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:49:57,976][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:49:58,485][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:49:58,994][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:49:59,505][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:50:00,014][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:50:00,524][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:50:01,034][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:50:01,544][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:50:02,054][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:50:02,563][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:50:03,073][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:50:03,583][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:50:04,092][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:50:04,603][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:50:05,113][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:50:05,624][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:50:06,133][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:50:06,643][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:50:07,153][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:50:07,662][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:50:08,172][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:50:08,682][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:50:09,192][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:50:09,700][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:50:10,209][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:50:10,718][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:50:11,227][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:50:11,735][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:50:12,244][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:50:12,753][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:50:13,262][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:50:13,770][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:50:14,279][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:50:14,788][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:50:15,296][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:50:15,806][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:50:16,315][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:50:16,825][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:50:17,334][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:50:17,844][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:50:18,353][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:50:18,861][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:50:19,370][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:50:19,878][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:50:20,386][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:50:20,895][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:50:21,407][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:50:21,919][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:50:22,431][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:50:22,944][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:50:23,457][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:50:23,968][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:50:24,480][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:50:24,992][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:50:25,503][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 22:50:26,168][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.32%, Current % of VRAM taken: 60.68%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:05 [2026-03-25 22:50:26,946][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:50:26,948][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:50:26,949][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:50:27,676][__main__][INFO] - Iteration 331 took 1m 16s (9.87% Gen, 89.17% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 56h 32m 39s. Estimated total time: 63h 47m 53s. Time estimates for 10 more iterations: 12m 45s, 100 more iterations: 2h 7m 35s, 500 more iterations: 10h 37m 58s. [2026-03-25 22:50:27,678][__main__][INFO] - Starting iteration 331. [2026-03-25 22:50:28,078][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:50:28,079][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:50:35,287][__main__][INFO] - Number of regex retries in iteration 331: 0 [2026-03-25 22:50:35,288][__main__][INFO] - agents played in iteration 331 are Bob, Alice [2026-03-25 22:50:36,252][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:50:36,878][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:50:37,343][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:50:37,856][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:50:38,366][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:50:38,874][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:50:39,382][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:50:39,890][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:50:40,398][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:50:40,906][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:50:41,412][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:50:41,919][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:50:42,428][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:50:42,936][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:50:43,444][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:50:43,955][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:50:44,463][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:50:44,970][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:50:45,478][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:50:45,986][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:50:46,494][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:50:47,002][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:50:47,510][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:50:48,018][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:50:48,527][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:50:49,035][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:50:49,544][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:50:50,050][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:50:50,557][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:50:51,065][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:50:51,572][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:50:52,080][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:50:52,586][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:50:53,093][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:50:53,602][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:50:54,110][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:50:54,618][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:50:55,126][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:50:55,635][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:50:56,145][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:50:56,652][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:50:57,165][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:50:57,677][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:50:58,186][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:50:58,696][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:50:59,207][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:50:59,718][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:51:00,228][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:51:00,737][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:51:01,247][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:51:01,770][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:51:02,280][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:51:02,789][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:51:03,298][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:51:03,806][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:51:04,316][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:51:04,826][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:51:05,336][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:51:05,845][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:51:06,357][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:51:06,865][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:51:07,373][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:51:07,884][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:51:08,392][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:51:08,900][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:51:09,409][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:51:09,917][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:51:10,425][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:51:10,935][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:51:11,445][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:51:11,954][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:51:12,462][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:51:12,971][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:51:13,480][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:51:13,989][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:51:14,497][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:51:15,007][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:51:15,515][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:51:16,025][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:51:16,534][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:51:17,041][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:51:17,549][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:51:18,058][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:51:18,565][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:51:19,073][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:51:19,583][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:51:20,090][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:51:20,598][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:51:21,106][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:51:21,614][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:51:22,122][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:51:22,629][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:51:23,136][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:51:23,645][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:51:24,153][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:51:24,660][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:51:25,167][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:51:25,674][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:51:26,182][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:51:26,691][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:51:27,200][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:51:27,708][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:51:28,216][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:51:28,725][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:51:29,234][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:51:29,743][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:51:30,252][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:51:30,760][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:51:31,269][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:51:31,778][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:51:32,287][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:51:32,794][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:51:33,304][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:51:33,814][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:51:34,322][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:51:34,830][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:51:35,338][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:51:35,846][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:51:36,354][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:51:36,862][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:51:37,370][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:51:37,878][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:51:38,386][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:51:38,894][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:51:39,403][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:51:39,911][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:51:40,420][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:51:40,928][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:51:41,437][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:51:41,944][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-25 22:51:42,601][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 22:51:43,363][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:51:43,365][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:51:43,367][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:51:44,106][__main__][INFO] - Iteration 332 took 1m 16s (9.48% Gen, 89.54% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 56h 4m 53s. Estimated total time: 63h 21m 23s. Time estimates for 10 more iterations: 12m 40s, 100 more iterations: 2h 6m 42s, 500 more iterations: 10h 33m 33s. [2026-03-25 22:51:44,108][__main__][INFO] - Starting iteration 332. [2026-03-25 22:51:44,509][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:51:44,510][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:51:47,399][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:51:50,943][__main__][INFO] - Number of regex retries in iteration 332: 1 [2026-03-25 22:51:50,944][__main__][INFO] - agents played in iteration 332 are Bob, Alice [2026-03-25 22:51:51,912][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:51:52,539][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:51:53,003][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:51:53,516][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:51:54,025][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:51:54,533][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:51:55,042][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:51:55,550][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:51:56,058][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:51:56,568][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:51:57,075][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:51:57,585][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:51:58,093][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:51:58,601][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:51:59,109][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:51:59,617][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:52:00,126][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:52:00,635][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:52:01,145][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:52:01,653][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:52:02,161][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:52:02,670][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:52:03,177][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:52:03,685][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:52:04,193][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:52:04,702][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:52:05,213][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:52:05,723][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:52:06,233][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:52:06,743][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:52:07,252][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:52:07,761][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:52:08,270][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:52:08,779][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:52:09,287][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:52:09,794][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:52:10,301][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:52:10,808][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:52:11,315][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:52:11,823][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:52:12,330][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:52:12,838][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:52:13,346][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:52:13,854][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:52:14,362][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:52:14,871][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:52:15,379][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:52:15,886][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:52:16,394][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:52:16,905][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:52:17,415][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:52:17,923][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:52:18,431][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:52:18,939][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:52:19,447][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:52:19,955][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:52:20,462][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:52:20,970][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:52:21,479][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:52:21,988][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:52:22,495][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:52:23,006][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:52:23,514][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:52:24,023][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:52:24,531][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:52:25,040][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:52:25,548][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:52:26,056][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:52:26,565][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:52:27,074][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:52:27,582][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:52:28,091][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:52:28,599][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:52:29,109][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:52:29,617][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:52:30,125][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:52:30,635][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:52:31,143][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:52:31,650][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:52:32,157][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:52:32,665][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:52:33,173][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:52:33,681][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:52:34,189][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:52:34,697][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:52:35,205][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:52:35,713][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:52:36,223][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:52:36,731][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:52:37,240][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:52:37,749][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:52:38,258][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:52:38,767][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:52:39,277][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:52:39,786][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:52:40,295][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:52:40,804][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:52:41,313][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:52:41,822][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:52:42,330][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:52:42,837][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:52:43,344][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:52:43,852][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:52:44,360][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:52:44,868][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:52:45,375][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:52:45,885][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:52:46,393][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:52:46,901][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:52:47,410][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:52:47,919][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:52:48,427][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:52:48,935][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:52:49,445][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:52:49,953][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:52:50,462][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:52:50,970][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:52:51,479][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:52:51,987][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:52:52,495][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:52:53,003][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:52:53,512][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:52:54,022][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:52:54,530][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:52:55,039][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:52:55,548][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:52:56,057][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:52:56,565][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:52:57,073][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:52:57,583][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 22:52:58,239][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 22:52:58,990][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:52:58,992][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:52:58,994][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:52:59,719][__main__][INFO] - Iteration 333 took 1m 15s (8.56% Gen, 90.48% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 22m 46s. Estimated total time: 62h 40m 32s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 21s, 500 more iterations: 10h 26m 45s. [2026-03-25 22:52:59,721][__main__][INFO] - Starting iteration 333. [2026-03-25 22:53:00,123][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:53:00,124][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:53:07,161][__main__][INFO] - Number of regex retries in iteration 333: 0 [2026-03-25 22:53:07,162][__main__][INFO] - agents played in iteration 333 are Bob, Alice [2026-03-25 22:53:08,126][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:53:08,754][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:53:09,217][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:53:09,730][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:53:10,238][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:53:10,746][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:53:11,254][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:53:11,762][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:53:12,269][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:53:12,776][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:53:13,281][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:53:13,785][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:53:14,291][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:53:14,798][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:53:15,304][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:53:15,809][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:53:16,314][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:53:16,819][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:53:17,330][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:53:17,838][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:53:18,348][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:53:18,856][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:53:19,364][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:53:19,873][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:53:20,381][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:53:20,890][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:53:21,401][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:53:21,910][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:53:22,419][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:53:22,928][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:53:23,437][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:53:23,945][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:53:24,454][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:53:24,964][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:53:25,472][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:53:25,979][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:53:26,486][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:53:26,993][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:53:27,500][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:53:28,008][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:53:28,515][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:53:29,024][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:53:29,533][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:53:30,042][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:53:30,550][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:53:31,059][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:53:31,567][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:53:32,076][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:53:32,585][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:53:33,094][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:53:33,603][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:53:34,111][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:53:34,621][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:53:35,130][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:53:35,639][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:53:36,148][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:53:36,657][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:53:37,166][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:53:37,695][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:53:38,208][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:53:38,719][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:53:39,231][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:53:39,742][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:53:40,253][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:53:40,764][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:53:41,275][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:53:41,783][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:53:42,290][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:53:42,799][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:53:43,306][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:53:43,814][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:53:44,321][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:53:44,830][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:53:45,339][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:53:45,844][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:53:46,348][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:53:46,855][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:53:47,362][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:53:47,867][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:53:48,371][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:53:48,875][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:53:49,381][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:53:49,889][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:53:50,397][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:53:50,905][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:53:51,413][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:53:51,922][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:53:52,430][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:53:52,938][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:53:53,447][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:53:53,956][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:53:54,466][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:53:54,974][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:53:55,484][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:53:55,992][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:53:56,501][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:53:57,010][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:53:57,519][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:53:58,028][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:53:58,535][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:53:59,044][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:53:59,552][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:54:00,059][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:54:00,568][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:54:01,076][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:54:01,583][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:54:02,091][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:54:02,600][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:54:03,108][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:54:03,617][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:54:04,128][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:54:04,636][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:54:05,145][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:54:05,654][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:54:06,163][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:54:06,671][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:54:07,180][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:54:07,688][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:54:08,196][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:54:08,705][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:54:09,214][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:54:09,724][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:54:10,236][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:54:10,748][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:54:11,258][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:54:11,768][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:54:12,279][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:54:12,788][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:54:13,298][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:54:13,810][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-25 22:54:14,469][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.32%, Current % of VRAM taken: 60.68%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:05 [2026-03-25 22:54:15,230][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:54:15,232][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:54:15,234][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:54:15,895][__main__][INFO] - Iteration 334 took 1m 15s (9.29% Gen, 89.84% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 49m 36s. Estimated total time: 63h 8m 38s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 17s, 500 more iterations: 10h 31m 26s. [2026-03-25 22:54:15,897][__main__][INFO] - Starting iteration 334. [2026-03-25 22:54:16,299][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:54:16,300][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:54:21,579][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:54:23,329][__main__][INFO] - Number of regex retries in iteration 334: 1 [2026-03-25 22:54:23,330][__main__][INFO] - agents played in iteration 334 are Bob, Alice [2026-03-25 22:54:24,300][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:54:24,929][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:54:25,393][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:54:25,907][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:54:26,415][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:54:26,925][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:54:27,433][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:54:27,942][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:54:28,451][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:54:28,959][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:54:29,470][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:54:29,980][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:54:30,489][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:54:30,997][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:54:31,506][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:54:32,015][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:54:32,525][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:54:33,034][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:54:33,546][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:54:34,056][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:54:34,565][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:54:35,075][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:54:35,584][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:54:36,094][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:54:36,603][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:54:37,112][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:54:37,620][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:54:38,128][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:54:38,636][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:54:39,145][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:54:39,654][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:54:40,161][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:54:40,669][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:54:41,176][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:54:41,686][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:54:42,195][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:54:42,704][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:54:43,214][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:54:43,723][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:54:44,232][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:54:44,743][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:54:45,252][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:54:45,761][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:54:46,269][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:54:46,776][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:54:47,284][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:54:47,793][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:54:48,300][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:54:48,809][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:54:49,318][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:54:49,827][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:54:50,335][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:54:50,844][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:54:51,353][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:54:51,861][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:54:52,369][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:54:52,876][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:54:53,385][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:54:53,892][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:54:54,398][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:54:54,906][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:54:55,414][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:54:55,922][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:54:56,427][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:54:56,934][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:54:57,443][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:54:57,952][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:54:58,459][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:54:58,968][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:54:59,476][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:54:59,984][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:55:00,491][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:55:01,000][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:55:01,508][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:55:02,016][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:55:02,527][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:55:03,037][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:55:03,545][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:55:04,055][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:55:04,564][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:55:05,073][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:55:05,582][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:55:06,090][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:55:06,599][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:55:07,107][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:55:07,616][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:55:08,125][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:55:08,634][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:55:09,142][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:55:09,651][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:55:10,158][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:55:10,665][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:55:11,173][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:55:11,680][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:55:12,186][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:55:12,693][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:55:13,200][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:55:13,707][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:55:14,214][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:55:14,724][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:55:15,233][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:55:15,741][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:55:16,250][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:55:16,759][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:55:17,267][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:55:17,775][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:55:18,283][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:55:18,790][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:55:19,298][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:55:19,805][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:55:20,313][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:55:20,820][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:55:21,325][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:55:21,833][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:55:22,342][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:55:22,852][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:55:23,361][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:55:23,870][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:55:24,378][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:55:24,886][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:55:25,394][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:55:25,904][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:55:26,413][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:55:26,921][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:55:27,429][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:55:27,938][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:55:28,446][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:55:28,954][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:55:29,461][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:55:29,969][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-25 22:55:30,623][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 22:55:31,385][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:55:31,387][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:55:31,389][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:55:32,054][__main__][INFO] - Iteration 335 took 1m 15s (9.28% Gen, 89.84% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 47m 28s. Estimated total time: 63h 7m 47s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 15s, 500 more iterations: 10h 31m 17s. [2026-03-25 22:55:32,056][__main__][INFO] - Starting iteration 335. [2026-03-25 22:55:32,465][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:55:32,466][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:55:39,640][__main__][INFO] - Number of regex retries in iteration 335: 0 [2026-03-25 22:55:39,642][__main__][INFO] - agents played in iteration 335 are Bob, Alice [2026-03-25 22:55:40,877][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:55:41,502][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:55:41,966][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:55:42,478][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:55:42,986][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:55:43,494][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:55:44,002][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:55:44,509][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:55:45,017][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:55:45,526][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:55:46,036][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:55:46,545][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:55:47,053][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:55:47,562][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:55:48,070][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:55:48,578][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:55:49,086][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:55:49,594][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:55:50,102][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:55:50,610][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:55:51,118][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:55:51,626][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:55:52,135][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:55:52,645][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:55:53,154][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:55:53,662][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:55:54,167][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:55:54,672][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:55:55,178][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:55:55,682][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:55:56,186][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:55:56,691][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:55:57,196][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:55:57,701][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:55:58,205][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:55:58,709][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:55:59,213][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:55:59,717][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:56:00,223][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:56:00,727][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:56:01,232][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:56:01,736][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:56:02,247][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:56:02,757][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:56:03,266][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:56:03,776][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:56:04,286][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:56:04,795][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:56:05,305][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:56:05,815][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:56:06,323][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:56:06,831][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:56:07,338][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:56:07,847][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:56:08,355][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:56:08,862][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:56:09,370][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:56:09,878][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:56:10,386][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:56:10,895][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:56:11,406][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:56:11,916][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:56:12,423][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:56:12,932][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:56:13,441][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:56:13,950][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:56:14,458][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:56:14,966][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:56:15,473][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:56:15,981][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:56:16,489][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:56:16,996][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:56:17,505][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:56:18,013][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:56:18,521][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:56:19,030][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:56:19,538][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:56:20,048][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:56:20,555][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:56:21,066][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:56:21,574][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:56:22,082][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:56:22,590][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:56:23,099][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:56:23,607][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:56:24,115][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:56:24,626][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:56:25,134][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:56:25,642][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:56:26,150][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:56:26,654][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:56:27,160][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:56:27,666][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:56:28,170][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:56:28,673][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:56:29,178][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:56:29,683][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:56:30,189][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:56:30,693][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:56:31,197][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:56:31,704][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:56:32,210][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:56:32,714][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:56:33,218][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:56:33,725][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:56:34,230][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:56:34,739][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:56:35,248][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:56:35,757][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:56:36,266][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:56:36,775][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:56:37,284][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:56:37,793][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:56:38,303][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:56:38,811][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:56:39,320][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:56:39,827][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:56:40,336][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:56:40,844][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:56:41,353][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:56:41,863][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:56:42,371][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:56:42,880][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:56:43,387][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:56:43,895][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:56:44,403][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:56:44,910][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:56:45,419][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:56:45,927][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:56:46,436][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 22:56:47,093][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 22:56:47,846][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:56:47,848][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:56:47,850][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:56:48,524][__main__][INFO] - Iteration 336 took 1m 16s (9.43% Gen, 89.68% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 56h 1m 23s. Estimated total time: 63h 22m 58s. Time estimates for 10 more iterations: 12m 40s, 100 more iterations: 2h 6m 45s, 500 more iterations: 10h 33m 49s. [2026-03-25 22:56:48,526][__main__][INFO] - Starting iteration 336. [2026-03-25 22:56:48,930][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:56:48,931][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:56:50,752][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:56:55,874][__main__][INFO] - Number of regex retries in iteration 336: 1 [2026-03-25 22:56:55,875][__main__][INFO] - agents played in iteration 336 are Bob, Alice [2026-03-25 22:56:56,838][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:56:57,466][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:56:57,929][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:56:58,444][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:56:58,953][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:56:59,461][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:56:59,969][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:57:00,477][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:57:00,985][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:57:01,494][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:57:02,005][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:57:02,515][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:57:03,024][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:57:03,534][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:57:04,045][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:57:04,555][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:57:05,063][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:57:05,572][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:57:06,083][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:57:06,591][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:57:07,100][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:57:07,608][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:57:08,116][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:57:08,626][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:57:09,135][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:57:09,645][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:57:10,157][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:57:10,666][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:57:11,179][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:57:11,689][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:57:12,198][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:57:12,708][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:57:13,218][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:57:13,728][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:57:14,236][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:57:14,746][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:57:15,253][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:57:15,761][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:57:16,269][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:57:16,776][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:57:17,285][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:57:17,793][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:57:18,301][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:57:18,809][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:57:19,318][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:57:19,827][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:57:20,335][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:57:20,845][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:57:21,355][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:57:21,864][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:57:22,372][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:57:22,882][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:57:23,390][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:57:23,898][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:57:24,406][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:57:24,915][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:57:25,425][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:57:25,934][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:57:26,444][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:57:26,952][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:57:27,460][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:57:27,968][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:57:28,476][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:57:28,984][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:57:29,492][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:57:30,001][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:57:30,510][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:57:31,018][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:57:31,527][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:57:32,036][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:57:32,545][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:57:33,053][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:57:33,561][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:57:34,070][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:57:34,578][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:57:35,086][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:57:35,595][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:57:36,104][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:57:36,614][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:57:37,122][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:57:37,630][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:57:38,140][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:57:38,649][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:57:39,157][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:57:39,666][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:57:40,175][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:57:40,684][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:57:41,192][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:57:41,703][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:57:42,212][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:57:42,722][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:57:43,232][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:57:43,742][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:57:44,252][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:57:44,761][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:57:45,271][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:57:45,781][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:57:46,290][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:57:46,797][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:57:47,307][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:57:47,817][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:57:48,324][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:57:48,833][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:57:49,341][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:57:49,849][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:57:50,357][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:57:50,865][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:57:51,374][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:57:51,882][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:57:52,391][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:57:52,899][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:57:53,407][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:57:53,916][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:57:54,426][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:57:54,935][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:57:55,443][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:57:55,951][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:57:56,458][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:57:56,967][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:57:57,475][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:57:57,983][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:57:58,490][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:57:58,999][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:57:59,507][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:58:00,015][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:58:00,525][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:58:01,034][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:58:01,542][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:58:02,049][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:58:02,557][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21726 tokens. [2026-03-25 22:58:03,220][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-25 22:58:03,976][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:58:03,978][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:58:03,980][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:58:05,002][__main__][INFO] - Iteration 337 took 1m 16s (9.13% Gen, 89.53% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 56h 0m 43s. Estimated total time: 63h 23m 35s. Time estimates for 10 more iterations: 12m 40s, 100 more iterations: 2h 6m 47s, 500 more iterations: 10h 33m 55s. [2026-03-25 22:58:05,004][__main__][INFO] - Starting iteration 337. [2026-03-25 22:58:05,407][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:58:05,408][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:58:12,171][__main__][INFO] - Number of regex retries in iteration 337: 0 [2026-03-25 22:58:12,172][__main__][INFO] - agents played in iteration 337 are Bob, Alice [2026-03-25 22:58:13,132][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:58:13,757][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:58:14,223][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:58:14,738][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:58:15,249][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:58:15,757][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:58:16,266][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:58:16,775][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:58:17,284][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:58:17,793][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:58:18,301][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:58:18,810][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:58:19,318][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:58:19,827][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:58:20,335][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:58:20,844][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:58:21,353][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:58:21,860][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:58:22,369][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:58:22,877][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:58:23,386][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:58:23,894][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:58:24,406][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:58:24,916][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:58:25,427][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:58:25,936][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:58:26,446][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:58:26,955][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:58:27,464][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:58:27,973][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:58:28,482][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:58:28,991][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:58:29,501][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:58:30,011][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:58:30,521][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:58:31,030][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:58:31,539][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:58:32,049][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:58:32,558][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:58:33,068][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:58:33,579][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:58:34,088][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:58:34,597][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:58:35,105][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:58:35,613][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:58:36,122][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:58:36,631][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:58:37,139][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:58:37,648][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:58:38,156][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:58:38,667][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:58:39,176][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:58:39,685][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:58:40,195][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:58:40,705][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:58:41,213][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:58:41,723][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:58:42,232][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:58:42,742][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:58:43,251][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 22:58:43,760][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 22:58:44,270][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 22:58:44,779][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 22:58:45,289][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 22:58:45,798][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 22:58:46,308][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 22:58:46,817][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 22:58:47,327][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 22:58:47,836][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 22:58:48,347][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 22:58:48,858][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 22:58:49,368][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 22:58:49,877][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 22:58:50,386][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 22:58:50,895][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 22:58:51,405][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 22:58:51,915][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 22:58:52,426][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 22:58:52,935][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 22:58:53,444][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 22:58:53,954][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 22:58:54,463][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 22:58:54,972][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 22:58:55,484][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 22:58:55,994][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 22:58:56,503][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 22:58:57,012][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 22:58:57,522][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 22:58:58,032][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 22:58:58,542][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 22:58:59,051][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 22:58:59,559][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 22:59:00,067][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 22:59:00,576][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 22:59:01,084][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 22:59:01,593][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 22:59:02,100][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 22:59:02,608][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 22:59:03,117][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 22:59:03,627][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 22:59:04,136][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 22:59:04,646][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 22:59:05,156][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 22:59:05,665][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 22:59:06,174][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 22:59:06,685][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 22:59:07,193][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 22:59:07,702][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 22:59:08,210][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 22:59:08,719][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 22:59:09,227][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 22:59:09,736][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 22:59:10,245][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 22:59:10,753][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 22:59:11,261][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 22:59:11,770][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 22:59:12,279][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 22:59:12,787][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 22:59:13,295][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 22:59:13,805][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 22:59:14,313][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 22:59:14,823][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 22:59:15,334][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 22:59:15,842][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 22:59:16,351][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 22:59:16,861][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 22:59:17,371][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 22:59:17,880][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 22:59:18,390][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 22:59:18,898][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 22:59:19,562][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-25 22:59:20,327][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 22:59:20,329][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 22:59:20,331][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 22:59:21,207][__main__][INFO] - Iteration 338 took 1m 15s (8.92% Gen, 89.92% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 45m 54s. Estimated total time: 63h 10m 1s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 20s, 500 more iterations: 10h 31m 40s. [2026-03-25 22:59:21,209][__main__][INFO] - Starting iteration 338. [2026-03-25 22:59:21,610][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 22:59:21,611][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 22:59:22,247][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:59:22,823][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 22:59:28,591][__main__][INFO] - Number of regex retries in iteration 338: 2 [2026-03-25 22:59:28,592][__main__][INFO] - agents played in iteration 338 are Bob, Alice [2026-03-25 22:59:29,532][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 22:59:30,150][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 22:59:30,617][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 22:59:31,131][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 22:59:31,641][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 22:59:32,151][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 22:59:32,660][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 22:59:33,169][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 22:59:33,680][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 22:59:34,189][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 22:59:34,696][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 22:59:35,204][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 22:59:35,712][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 22:59:36,219][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 22:59:36,727][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 22:59:37,234][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 22:59:37,740][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 22:59:38,247][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 22:59:38,754][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 22:59:39,262][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 22:59:39,769][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 22:59:40,276][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 22:59:40,784][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 22:59:41,292][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 22:59:41,800][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 22:59:42,307][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 22:59:42,815][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 22:59:43,323][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 22:59:43,831][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 22:59:44,340][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 22:59:44,847][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 22:59:45,355][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 22:59:45,863][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 22:59:46,372][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 22:59:46,881][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 22:59:47,389][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 22:59:47,896][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 22:59:48,407][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 22:59:48,916][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 22:59:49,424][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 22:59:49,933][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 22:59:50,441][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 22:59:50,948][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 22:59:51,456][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 22:59:51,966][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 22:59:52,474][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 22:59:52,983][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 22:59:53,491][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 22:59:54,000][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 22:59:54,508][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 22:59:55,012][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 22:59:55,516][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 22:59:56,021][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 22:59:56,529][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 22:59:57,035][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 22:59:57,539][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 22:59:58,043][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 22:59:58,547][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 22:59:59,055][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 22:59:59,563][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:00:00,071][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:00:00,579][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:00:01,087][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:00:01,595][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:00:02,104][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:00:02,612][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:00:03,121][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:00:03,630][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:00:04,139][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:00:04,649][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:00:05,158][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:00:05,666][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:00:06,175][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:00:06,684][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:00:07,190][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:00:07,697][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:00:08,205][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:00:08,713][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:00:09,220][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:00:09,728][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:00:10,235][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:00:10,745][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:00:11,254][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:00:11,762][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:00:12,270][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:00:12,778][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:00:13,285][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:00:13,793][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:00:14,303][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:00:14,812][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:00:15,321][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:00:15,828][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:00:16,336][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:00:16,845][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:00:17,353][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:00:17,862][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:00:18,369][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:00:18,877][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:00:19,386][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:00:19,894][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:00:20,403][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:00:20,911][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:00:21,419][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:00:21,927][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:00:22,435][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:00:22,944][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:00:23,453][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:00:23,962][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:00:24,472][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:00:24,980][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:00:25,488][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:00:25,996][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:00:26,506][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:00:27,015][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:00:27,520][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:00:28,025][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:00:28,531][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:00:29,036][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:00:29,541][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:00:30,045][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:00:30,550][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:00:31,056][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:00:31,565][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:00:32,072][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:00:32,581][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:00:33,089][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:00:33,596][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:00:34,105][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:00:34,613][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:00:35,122][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 23:00:35,772][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 23:00:36,523][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:00:36,525][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:00:36,527][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:00:37,259][__main__][INFO] - Iteration 339 took 1m 15s (9.23% Gen, 89.80% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 55h 37m 5s. Estimated total time: 63h 2m 29s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 4s, 500 more iterations: 10h 30m 24s. [2026-03-25 23:00:37,261][__main__][INFO] - Starting iteration 339. [2026-03-25 23:00:37,662][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 23:00:37,663][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:00:40,398][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:00:40,931][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:00:44,231][__main__][INFO] - Number of regex retries in iteration 339: 2 [2026-03-25 23:00:44,232][__main__][INFO] - agents played in iteration 339 are Bob, Alice [2026-03-25 23:00:45,194][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:00:45,825][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:00:46,289][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:00:46,804][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:00:47,313][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:00:47,826][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:00:48,336][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:00:48,846][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:00:49,354][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:00:49,865][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:00:50,374][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:00:50,882][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:00:51,389][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:00:51,897][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:00:52,406][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:00:52,915][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:00:53,423][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:00:53,931][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:00:54,441][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:00:54,948][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:00:55,455][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:00:55,964][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:00:56,472][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:00:56,980][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:00:57,487][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:00:57,995][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:00:58,503][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:00:59,012][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:00:59,519][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:01:00,028][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:01:00,536][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:01:01,045][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:01:01,554][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:01:02,062][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:01:02,570][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:01:03,077][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:01:03,586][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:01:04,095][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:01:04,602][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:01:05,110][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:01:05,618][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:01:06,128][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:01:06,635][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:01:07,141][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:01:07,648][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:01:08,156][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:01:08,662][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:01:09,169][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:01:09,675][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:01:10,181][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:01:10,687][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:01:11,193][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:01:11,698][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:01:12,207][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:01:12,712][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:01:13,218][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:01:13,725][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:01:14,233][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:01:14,741][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:01:15,248][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:01:15,755][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:01:16,263][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:01:16,770][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:01:17,279][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:01:17,788][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:01:18,296][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:01:18,805][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:01:19,315][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:01:19,824][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:01:20,334][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:01:20,843][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:01:21,352][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:01:21,861][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:01:22,371][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:01:22,880][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:01:23,388][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:01:23,895][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:01:24,403][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:01:24,911][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:01:25,419][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:01:25,927][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:01:26,435][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:01:26,943][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:01:27,451][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:01:27,960][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:01:28,468][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:01:28,976][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:01:29,486][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:01:29,995][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:01:30,503][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:01:31,011][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:01:31,518][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:01:32,027][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:01:32,536][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:01:33,045][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:01:33,553][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:01:34,061][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:01:34,569][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:01:35,076][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:01:35,584][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:01:36,091][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:01:36,600][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:01:37,108][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:01:37,616][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:01:38,125][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:01:38,633][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:01:39,138][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:01:39,645][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:01:40,152][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:01:40,659][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:01:41,164][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:01:41,672][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:01:42,178][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:01:42,685][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:01:43,191][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:01:43,697][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:01:44,204][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:01:44,710][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:01:45,216][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:01:45,723][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:01:46,230][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:01:46,736][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:01:47,246][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:01:47,754][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:01:48,264][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:01:48,772][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:01:49,280][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:01:49,789][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:01:50,297][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:01:50,806][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21760 tokens. [2026-03-25 23:01:51,465][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-25 23:01:52,228][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:01:52,230][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:01:52,232][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:01:52,958][__main__][INFO] - Iteration 340 took 1m 15s (8.72% Gen, 90.31% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 55h 18m 9s. Estimated total time: 62h 44m 49s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 29s, 500 more iterations: 10h 27m 28s. [2026-03-25 23:01:52,960][__main__][INFO] - Starting iteration 340. [2026-03-25 23:01:53,361][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 23:01:53,362][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:01:53,994][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:01:58,618][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:02:00,190][__main__][INFO] - Number of regex retries in iteration 340: 2 [2026-03-25 23:02:00,191][__main__][INFO] - agents played in iteration 340 are Bob, Alice [2026-03-25 23:02:01,158][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:02:01,797][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:02:02,262][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:02:02,776][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:02:03,284][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:02:03,791][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:02:04,300][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:02:04,809][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:02:05,317][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:02:05,826][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:02:06,337][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:02:06,847][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:02:07,357][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:02:07,867][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:02:08,377][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:02:08,887][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:02:09,397][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:02:09,906][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:02:10,414][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:02:10,923][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:02:11,431][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:02:11,939][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:02:12,447][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:02:12,955][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:02:13,464][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:02:13,972][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:02:14,479][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:02:14,988][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:02:15,496][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:02:16,005][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:02:16,513][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:02:17,022][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:02:17,530][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:02:18,038][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:02:18,546][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:02:19,055][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:02:19,563][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:02:20,070][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:02:20,577][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:02:21,086][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:02:21,594][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:02:22,102][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:02:22,609][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:02:23,117][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:02:23,626][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:02:24,134][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:02:24,643][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:02:25,151][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:02:25,658][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:02:26,166][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:02:26,674][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:02:27,183][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:02:27,690][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:02:28,197][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:02:28,705][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:02:29,214][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:02:29,721][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:02:30,230][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:02:30,737][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:02:31,245][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:02:31,754][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:02:32,262][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:02:32,771][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:02:33,280][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:02:33,789][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:02:34,296][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:02:34,806][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:02:35,315][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:02:35,824][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:02:36,333][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:02:36,841][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:02:37,350][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:02:37,859][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:02:38,368][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:02:38,877][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:02:39,387][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:02:39,897][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:02:40,407][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:02:40,917][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:02:41,428][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:02:41,938][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:02:42,449][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:02:42,957][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:02:43,466][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:02:43,974][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:02:44,482][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:02:44,990][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:02:45,499][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:02:46,007][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:02:46,516][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:02:47,025][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:02:47,534][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:02:48,043][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:02:48,552][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:02:49,060][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:02:49,568][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:02:50,076][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:02:50,585][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:02:51,092][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:02:51,600][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:02:52,108][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:02:52,616][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:02:53,125][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:02:53,633][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:02:54,141][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:02:54,649][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:02:55,156][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:02:55,663][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:02:56,171][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:02:56,679][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:02:57,187][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:02:57,693][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:02:58,201][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:02:58,709][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:02:59,218][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:02:59,726][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:03:00,235][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:03:00,744][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:03:01,253][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:03:01,762][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:03:02,270][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:03:02,778][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:03:03,288][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:03:03,796][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:03:04,304][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:03:04,813][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:03:05,323][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:03:05,832][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:03:06,340][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:03:06,850][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21738 tokens. [2026-03-25 23:03:07,514][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 23:03:08,268][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:03:08,270][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:03:08,272][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:03:09,019][__main__][INFO] - Iteration 341 took 1m 15s (9.03% Gen, 89.98% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 34m 59s. Estimated total time: 63h 2m 55s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 5s, 500 more iterations: 10h 30m 29s. [2026-03-25 23:03:09,021][__main__][INFO] - Starting iteration 341. [2026-03-25 23:03:09,423][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 23:03:09,424][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:03:16,083][__main__][INFO] - Number of regex retries in iteration 341: 0 [2026-03-25 23:03:16,084][__main__][INFO] - agents played in iteration 341 are Bob, Alice [2026-03-25 23:03:17,047][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:03:17,674][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:03:18,137][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:03:18,649][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:03:19,156][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:03:19,664][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:03:20,172][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:03:20,679][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:03:21,185][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:03:21,692][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:03:22,205][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:03:22,716][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:03:23,227][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:03:23,737][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:03:24,247][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:03:24,757][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:03:25,268][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:03:25,778][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:03:26,286][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:03:26,793][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:03:27,304][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:03:27,812][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:03:28,320][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:03:28,828][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:03:29,337][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:03:29,845][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:03:30,350][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:03:30,855][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:03:31,361][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:03:31,866][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:03:32,371][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:03:32,876][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:03:33,382][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:03:33,887][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:03:34,395][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:03:34,904][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:03:35,412][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:03:35,922][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:03:36,431][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:03:36,939][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:03:37,448][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:03:37,957][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:03:38,465][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:03:38,972][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:03:39,481][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:03:39,990][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:03:40,498][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:03:41,006][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:03:41,514][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:03:42,022][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:03:42,532][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:03:43,041][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:03:43,550][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:03:44,060][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:03:44,569][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:03:45,078][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:03:45,587][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:03:46,096][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:03:46,605][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:03:47,114][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:03:47,622][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:03:48,132][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:03:48,641][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:03:49,150][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:03:49,660][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:03:50,169][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:03:50,678][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:03:51,186][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:03:51,695][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:03:52,205][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:03:52,714][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:03:53,221][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:03:53,729][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:03:54,238][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:03:54,748][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:03:55,259][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:03:55,771][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:03:56,282][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:03:56,792][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:03:57,304][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:03:57,815][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:03:58,327][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:03:58,836][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:03:59,344][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:03:59,852][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:04:00,359][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:04:00,868][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:04:01,375][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:04:01,884][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:04:02,391][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:04:02,896][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:04:03,401][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:04:03,906][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:04:04,412][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:04:04,916][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:04:05,420][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:04:05,926][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:04:06,431][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:04:06,939][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:04:07,445][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:04:07,951][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:04:08,460][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:04:08,968][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:04:09,476][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:04:09,984][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:04:10,492][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:04:10,999][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:04:11,507][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:04:12,014][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:04:12,523][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:04:13,031][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:04:13,538][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:04:14,046][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:04:14,553][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:04:15,062][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:04:15,570][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:04:16,079][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:04:16,587][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:04:17,094][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:04:17,603][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:04:18,111][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:04:18,621][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:04:19,129][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:04:19,636][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:04:20,145][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:04:20,654][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:04:21,162][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:04:21,670][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:04:22,178][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:04:22,686][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 23:04:23,339][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-25 23:04:24,097][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:04:24,099][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:04:24,101][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:04:24,764][__main__][INFO] - Iteration 342 took 1m 15s (8.84% Gen, 90.28% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 17m 52s. Estimated total time: 62h 47m 3s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 34s, 500 more iterations: 10h 27m 50s. [2026-03-25 23:04:24,766][__main__][INFO] - Starting iteration 342. [2026-03-25 23:04:25,168][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 23:04:25,169][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:04:31,457][__main__][INFO] - Number of regex retries in iteration 342: 0 [2026-03-25 23:04:31,458][__main__][INFO] - agents played in iteration 342 are Bob, Alice [2026-03-25 23:04:32,372][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:04:32,993][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:04:33,455][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:04:33,970][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:04:34,477][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:04:34,985][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:04:35,492][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:04:35,997][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:04:36,503][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:04:37,010][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:04:37,522][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:04:38,031][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:04:38,540][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:04:39,049][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:04:39,559][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:04:40,067][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:04:40,576][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:04:41,086][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:04:41,594][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:04:42,103][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:04:42,612][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:04:43,122][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:04:43,631][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:04:44,141][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:04:44,651][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:04:45,160][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:04:45,668][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:04:46,175][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:04:46,683][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:04:47,191][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:04:47,698][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:04:48,206][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:04:48,714][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:04:49,223][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:04:49,733][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:04:50,244][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:04:50,754][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:04:51,262][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:04:51,771][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:04:52,280][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:04:52,789][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:04:53,298][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:04:53,807][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:04:54,317][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:04:54,827][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:04:55,336][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:04:55,847][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:04:56,357][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:04:56,866][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:04:57,377][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:04:57,889][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:04:58,399][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:04:58,909][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:04:59,420][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:04:59,931][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:05:00,441][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:05:00,951][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:05:01,462][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:05:01,972][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:05:02,480][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:05:02,990][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:05:03,499][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:05:04,008][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:05:04,516][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:05:05,026][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:05:05,535][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:05:06,041][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:05:06,548][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:05:07,055][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:05:07,562][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:05:08,067][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:05:08,573][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:05:09,080][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:05:09,587][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:05:10,096][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:05:10,605][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:05:11,114][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:05:11,625][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:05:12,134][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:05:12,645][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:05:13,154][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:05:13,663][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:05:14,171][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:05:14,679][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:05:15,186][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:05:15,694][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:05:16,204][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:05:16,713][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:05:17,220][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:05:17,728][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:05:18,235][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:05:18,743][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:05:19,251][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:05:19,759][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:05:20,266][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:05:20,773][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:05:21,281][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:05:21,789][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:05:22,297][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:05:22,806][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:05:23,315][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:05:23,824][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:05:24,333][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:05:24,843][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:05:25,351][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:05:25,861][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:05:26,370][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:05:26,879][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:05:27,389][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:05:27,898][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:05:28,407][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:05:28,916][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:05:29,427][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:05:29,937][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:05:30,447][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:05:30,957][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:05:31,466][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:05:31,975][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:05:32,484][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:05:32,993][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:05:33,506][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:05:34,017][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:05:34,527][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:05:35,036][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:05:35,545][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:05:36,054][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:05:36,564][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:05:37,074][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:05:37,584][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:05:38,093][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 23:05:38,766][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 23:05:39,541][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:05:39,543][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:05:39,545][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:05:40,221][__main__][INFO] - Iteration 343 took 1m 15s (8.38% Gen, 90.72% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 2m 12s. Estimated total time: 62h 32m 39s. Time estimates for 10 more iterations: 12m 30s, 100 more iterations: 2h 5m 5s, 500 more iterations: 10h 25m 26s. [2026-03-25 23:05:40,223][__main__][INFO] - Starting iteration 343. [2026-03-25 23:05:40,627][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 23:05:40,628][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:05:47,880][__main__][INFO] - Number of regex retries in iteration 343: 0 [2026-03-25 23:05:47,881][__main__][INFO] - agents played in iteration 343 are Bob, Alice [2026-03-25 23:05:48,835][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:05:49,456][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:05:49,921][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:05:50,434][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:05:50,942][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:05:51,451][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:05:51,959][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:05:52,467][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:05:52,975][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:05:53,483][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:05:53,987][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:05:54,491][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:05:54,995][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:05:55,501][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:05:56,005][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:05:56,510][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:05:57,014][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:05:57,518][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:05:58,028][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:05:58,536][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:05:59,044][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:05:59,553][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:06:00,062][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:06:00,570][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:06:01,076][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:06:01,585][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:06:02,093][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:06:02,601][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:06:03,109][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:06:03,618][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:06:04,127][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:06:04,636][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:06:05,146][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:06:05,655][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:06:06,165][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:06:06,674][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:06:07,184][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:06:07,693][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:06:08,201][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:06:08,709][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:06:09,218][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:06:09,727][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:06:10,234][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:06:10,744][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:06:11,251][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:06:11,757][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:06:12,265][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:06:12,772][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:06:13,280][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:06:13,787][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:06:14,300][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:06:14,811][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:06:15,321][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:06:15,832][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:06:16,342][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:06:16,851][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:06:17,362][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:06:17,872][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:06:18,380][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:06:18,888][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:06:19,397][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:06:19,905][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:06:20,414][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:06:20,922][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:06:21,432][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:06:21,941][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:06:22,450][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:06:22,959][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:06:23,468][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:06:23,976][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:06:24,485][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:06:24,993][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:06:25,502][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:06:26,011][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:06:26,516][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:06:27,021][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:06:27,528][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:06:28,032][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:06:28,536][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:06:29,041][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:06:29,546][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:06:30,051][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:06:30,558][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:06:31,067][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:06:31,575][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:06:32,083][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:06:32,591][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:06:33,099][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:06:33,609][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:06:34,116][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:06:34,625][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:06:35,133][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:06:35,641][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:06:36,149][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:06:36,656][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:06:37,164][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:06:37,671][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:06:38,178][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:06:38,687][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:06:39,195][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:06:39,703][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:06:40,211][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:06:40,721][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:06:41,226][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:06:41,734][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:06:42,244][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:06:42,751][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:06:43,259][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:06:43,767][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:06:44,275][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:06:44,783][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:06:45,290][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:06:45,796][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:06:46,306][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:06:46,817][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:06:47,327][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:06:47,837][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:06:48,347][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:06:48,857][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:06:49,367][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:06:49,877][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:06:50,387][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:06:50,896][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:06:51,405][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:06:51,914][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:06:52,423][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:06:52,931][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:06:53,440][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:06:53,949][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:06:54,458][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21736 tokens. [2026-03-25 23:06:55,118][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-25 23:06:55,877][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:06:55,879][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:06:55,881][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:06:56,610][__main__][INFO] - Iteration 344 took 1m 15s (9.55% Gen, 89.49% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 55h 47m 26s. Estimated total time: 63h 19m 9s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 38s, 500 more iterations: 10h 33m 11s. [2026-03-25 23:06:56,612][__main__][INFO] - Starting iteration 344. [2026-03-25 23:06:57,016][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 23:06:57,017][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:06:57,623][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:06:58,151][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:07:03,813][__main__][INFO] - Number of regex retries in iteration 344: 2 [2026-03-25 23:07:03,814][__main__][INFO] - agents played in iteration 344 are Bob, Alice [2026-03-25 23:07:04,771][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:07:05,395][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:07:05,860][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:07:06,372][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:07:06,881][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:07:07,389][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:07:07,897][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:07:08,407][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:07:08,916][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:07:09,426][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:07:09,938][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:07:10,447][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:07:10,956][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:07:11,466][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:07:11,975][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:07:12,484][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:07:12,993][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:07:13,503][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:07:14,010][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:07:14,518][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:07:15,026][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:07:15,534][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:07:16,043][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:07:16,550][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:07:17,058][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:07:17,565][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:07:18,072][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:07:18,580][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:07:19,088][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:07:19,596][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:07:20,104][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:07:20,612][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:07:21,120][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:07:21,629][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:07:22,137][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:07:22,645][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:07:23,154][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:07:23,662][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:07:24,170][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:07:24,678][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:07:25,186][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:07:25,695][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:07:26,204][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:07:26,712][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:07:27,219][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:07:27,727][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:07:28,235][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:07:28,744][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:07:29,251][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:07:29,759][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:07:30,268][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:07:30,777][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:07:31,285][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:07:31,793][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:07:32,302][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:07:32,809][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:07:33,317][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:07:33,826][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:07:34,334][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:07:34,842][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:07:35,350][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:07:35,859][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:07:36,368][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:07:36,876][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:07:37,383][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:07:37,892][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:07:38,400][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:07:38,908][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:07:39,416][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:07:39,927][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:07:40,436][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:07:40,944][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:07:41,452][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:07:41,961][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:07:42,470][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:07:42,979][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:07:43,488][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:07:43,997][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:07:44,505][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:07:45,013][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:07:45,524][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:07:46,034][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:07:46,543][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:07:47,052][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:07:47,562][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:07:48,071][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:07:48,582][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:07:49,090][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:07:49,599][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:07:50,107][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:07:50,615][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:07:51,126][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:07:51,635][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:07:52,142][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:07:52,651][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:07:53,159][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:07:53,666][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:07:54,174][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:07:54,682][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:07:55,191][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:07:55,699][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:07:56,208][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:07:56,716][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:07:57,225][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:07:57,734][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:07:58,242][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:07:58,750][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:07:59,257][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:07:59,765][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:08:00,272][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:08:00,780][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:08:01,287][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:08:01,795][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:08:02,302][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:08:02,811][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:08:03,321][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:08:03,829][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:08:04,338][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:08:04,848][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:08:05,357][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:08:05,866][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:08:06,374][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:08:06,884][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:08:07,392][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:08:07,901][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:08:08,408][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:08:08,916][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:08:09,425][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:08:09,934][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:08:10,444][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-25 23:08:11,105][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 23:08:11,861][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:08:11,863][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:08:11,865][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:08:12,543][__main__][INFO] - Iteration 345 took 1m 15s (9.00% Gen, 90.10% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 23m 23s. Estimated total time: 62h 56m 22s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 52s, 500 more iterations: 10h 29m 23s. [2026-03-25 23:08:12,545][__main__][INFO] - Starting iteration 345. [2026-03-25 23:08:12,948][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 23:08:12,949][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:08:20,399][__main__][INFO] - Number of regex retries in iteration 345: 0 [2026-03-25 23:08:20,400][__main__][INFO] - agents played in iteration 345 are Bob, Alice [2026-03-25 23:08:21,369][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:08:21,999][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:08:22,465][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:08:22,980][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:08:23,490][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:08:23,999][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:08:24,508][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:08:25,017][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:08:25,526][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:08:26,036][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:08:26,546][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:08:27,055][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:08:27,564][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:08:28,072][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:08:28,580][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:08:29,088][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:08:29,597][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:08:30,106][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:08:30,613][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:08:31,123][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:08:31,631][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:08:32,140][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:08:32,648][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:08:33,156][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:08:33,666][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:08:34,174][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:08:34,683][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:08:35,191][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:08:35,698][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:08:36,208][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:08:36,717][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:08:37,226][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:08:37,733][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:08:38,243][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:08:38,752][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:08:39,261][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:08:39,769][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:08:40,277][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:08:40,786][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:08:41,294][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:08:41,802][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:08:42,311][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:08:42,819][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:08:43,328][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:08:43,837][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:08:44,346][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:08:44,855][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:08:45,362][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:08:45,871][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:08:46,379][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:08:46,888][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:08:47,395][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:08:47,904][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:08:48,412][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:08:48,920][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:08:49,427][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:08:49,935][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:08:50,443][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:08:50,953][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:08:51,462][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:08:51,971][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:08:52,480][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:08:52,989][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:08:53,497][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:08:54,007][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:08:54,515][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:08:55,026][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:08:55,536][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:08:56,045][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:08:56,556][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:08:57,065][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:08:57,575][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:08:58,084][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:08:58,594][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:08:59,103][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:08:59,612][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:09:00,121][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:09:00,630][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:09:01,139][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:09:01,647][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:09:02,155][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:09:02,665][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:09:03,173][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:09:03,679][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:09:04,185][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:09:04,694][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:09:05,203][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:09:05,711][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:09:06,220][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:09:06,729][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:09:07,238][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:09:07,745][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:09:08,254][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:09:08,763][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:09:09,271][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:09:09,780][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:09:10,289][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:09:10,796][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:09:11,306][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:09:11,815][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:09:12,327][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:09:12,837][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:09:13,346][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:09:13,855][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:09:14,365][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:09:14,874][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:09:15,380][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:09:15,887][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:09:16,394][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:09:16,901][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:09:17,409][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:09:17,916][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:09:18,424][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:09:18,931][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:09:19,439][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:09:19,947][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:09:20,455][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:09:20,963][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:09:21,470][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:09:21,978][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:09:22,486][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:09:22,995][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:09:23,504][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:09:24,014][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:09:24,524][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:09:25,034][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:09:25,543][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:09:26,052][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:09:26,561][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:09:27,069][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 23:09:27,731][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:05 [2026-03-25 23:09:28,487][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:09:28,489][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:09:28,491][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:09:29,257][__main__][INFO] - Iteration 346 took 1m 16s (9.76% Gen, 89.23% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 56h 1m 14s. Estimated total time: 63h 35m 30s. Time estimates for 10 more iterations: 12m 43s, 100 more iterations: 2h 7m 11s, 500 more iterations: 10h 35m 55s. [2026-03-25 23:09:29,259][__main__][INFO] - Starting iteration 346. [2026-03-25 23:09:29,660][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 23:09:29,661][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:09:36,411][__main__][INFO] - Number of regex retries in iteration 346: 0 [2026-03-25 23:09:36,412][__main__][INFO] - agents played in iteration 346 are Bob, Alice [2026-03-25 23:09:37,374][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:09:38,006][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:09:38,471][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:09:38,985][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:09:39,493][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:09:40,001][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:09:40,510][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:09:41,018][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:09:41,526][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:09:42,035][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:09:42,547][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:09:43,056][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:09:43,565][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:09:44,074][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:09:44,583][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:09:45,093][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:09:45,602][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:09:46,111][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:09:46,623][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:09:47,133][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:09:47,643][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:09:48,154][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:09:48,664][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:09:49,174][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:09:49,682][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:09:50,191][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:09:50,701][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:09:51,210][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:09:51,718][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:09:52,228][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:09:52,738][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:09:53,247][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:09:53,756][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:09:54,266][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:09:54,774][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:09:55,283][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:09:55,791][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:09:56,300][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:09:56,808][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:09:57,316][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:09:57,826][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:09:58,335][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:09:58,844][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:09:59,353][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:09:59,864][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:10:00,373][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:10:00,882][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:10:01,390][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:10:01,899][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:10:02,407][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:10:02,914][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:10:03,424][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:10:03,933][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:10:04,440][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:10:04,948][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:10:05,456][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:10:05,964][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:10:06,472][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:10:06,980][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:10:07,488][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:10:07,996][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:10:08,504][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:10:09,012][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:10:09,520][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:10:10,028][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:10:10,536][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:10:11,044][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:10:11,552][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:10:12,060][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:10:12,568][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:10:13,075][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:10:13,584][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:10:14,092][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:10:14,600][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:10:15,107][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:10:15,615][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:10:16,125][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:10:16,633][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:10:17,142][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:10:17,651][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:10:18,159][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:10:18,668][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:10:19,177][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:10:19,686][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:10:20,195][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:10:20,705][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:10:21,214][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:10:21,724][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:10:22,234][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:10:22,746][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:10:23,255][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:10:23,763][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:10:24,272][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:10:24,781][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:10:25,289][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:10:25,798][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:10:26,306][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:10:26,814][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:10:27,323][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:10:27,831][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:10:28,339][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:10:28,848][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:10:29,355][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:10:29,863][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:10:30,372][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:10:30,881][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:10:31,389][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:10:31,897][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:10:32,408][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:10:32,918][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:10:33,426][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:10:33,935][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:10:34,444][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:10:34,953][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:10:35,462][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:10:35,970][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:10:36,477][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:10:36,985][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:10:37,493][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:10:38,002][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:10:38,510][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:10:39,018][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:10:39,527][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:10:40,035][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:10:40,543][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:10:41,052][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:10:41,559][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:10:42,067][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:10:42,575][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:10:43,083][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 23:10:43,735][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 23:10:44,492][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:10:44,496][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:10:44,499][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:10:45,307][__main__][INFO] - Iteration 347 took 1m 15s (8.92% Gen, 90.01% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 26m 49s. Estimated total time: 63h 2m 21s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 4s, 500 more iterations: 10h 30m 23s. [2026-03-25 23:10:45,309][__main__][INFO] - Starting iteration 347. [2026-03-25 23:10:45,711][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 23:10:45,712][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:10:52,817][__main__][INFO] - Number of regex retries in iteration 347: 0 [2026-03-25 23:10:52,818][__main__][INFO] - agents played in iteration 347 are Bob, Alice [2026-03-25 23:10:53,778][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:10:54,399][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:10:54,861][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:10:55,374][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:10:55,879][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:10:56,390][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:10:56,896][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:10:57,406][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:10:57,914][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:10:58,422][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:10:58,932][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:10:59,441][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:10:59,950][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:11:00,458][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:11:00,967][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:11:01,476][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:11:01,985][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:11:02,493][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:11:03,002][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:11:03,511][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:11:04,020][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:11:04,527][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:11:05,035][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:11:05,545][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:11:06,054][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:11:06,564][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:11:07,076][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:11:07,601][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:11:08,109][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:11:08,619][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:11:09,129][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:11:09,637][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:11:10,147][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:11:10,657][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:11:11,164][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:11:11,673][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:11:12,181][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:11:12,688][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:11:13,196][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:11:13,704][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:11:14,212][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:11:14,720][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:11:15,229][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:11:15,738][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:11:16,248][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:11:16,757][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:11:17,265][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:11:17,775][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:11:18,283][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:11:18,792][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:11:19,299][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:11:19,806][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:11:20,314][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:11:20,822][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:11:21,330][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:11:21,837][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:11:22,346][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:11:22,854][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:11:23,361][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:11:23,868][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:11:24,377][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:11:24,885][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:11:25,393][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:11:25,902][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:11:26,410][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:11:26,917][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:11:27,427][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:11:27,935][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:11:28,442][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:11:28,949][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:11:29,456][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:11:29,964][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:11:30,471][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:11:30,979][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:11:31,487][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:11:31,997][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:11:32,505][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:11:33,014][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:11:33,524][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:11:34,033][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:11:34,542][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:11:35,052][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:11:35,561][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:11:36,070][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:11:36,577][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:11:37,088][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:11:37,597][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:11:38,104][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:11:38,613][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:11:39,122][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:11:39,631][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:11:40,140][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:11:40,651][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:11:41,160][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:11:41,669][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:11:42,178][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:11:42,688][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:11:43,198][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:11:43,707][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:11:44,215][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:11:44,725][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:11:45,234][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:11:45,742][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:11:46,250][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:11:46,758][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:11:47,265][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:11:47,775][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:11:48,285][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:11:48,794][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:11:49,303][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:11:49,812][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:11:50,322][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:11:50,833][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:11:51,341][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:11:51,848][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:11:52,356][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:11:52,864][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:11:53,371][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:11:53,878][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:11:54,386][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:11:54,893][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:11:55,400][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:11:55,908][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:11:56,415][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:11:56,924][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:11:57,432][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:11:57,940][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:11:58,448][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:11:58,956][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:11:59,465][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21725 tokens. [2026-03-25 23:12:00,116][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 23:12:00,872][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:12:00,875][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:12:00,876][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:12:01,545][__main__][INFO] - Iteration 348 took 1m 15s (9.37% Gen, 89.75% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 34m 54s. Estimated total time: 63h 11m 42s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 23s, 500 more iterations: 10h 31m 57s. [2026-03-25 23:12:01,547][__main__][INFO] - Starting iteration 348. [2026-03-25 23:12:01,948][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 23:12:01,949][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:12:09,238][__main__][INFO] - Number of regex retries in iteration 348: 0 [2026-03-25 23:12:09,239][__main__][INFO] - agents played in iteration 348 are Bob, Alice [2026-03-25 23:12:10,205][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:12:10,834][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:12:11,298][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:12:11,811][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:12:12,319][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:12:12,828][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:12:13,336][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:12:13,845][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:12:14,352][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:12:14,860][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:12:15,368][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:12:15,876][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:12:16,384][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:12:16,892][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:12:17,400][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:12:17,908][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:12:18,415][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:12:18,919][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:12:19,431][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:12:19,940][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:12:20,449][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:12:20,957][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:12:21,467][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:12:21,976][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:12:22,484][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:12:22,992][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:12:23,503][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:12:24,012][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:12:24,521][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:12:25,031][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:12:25,540][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:12:26,049][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:12:26,556][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:12:27,067][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:12:27,595][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:12:28,109][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:12:28,618][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:12:29,128][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:12:29,638][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:12:30,148][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:12:30,659][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:12:31,168][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:12:31,686][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:12:32,213][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:12:35,205][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:12:35,717][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:12:36,226][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:12:36,737][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:12:37,246][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:12:37,755][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:12:38,266][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:12:38,775][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:12:39,285][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:12:39,794][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:12:40,303][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:12:40,812][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:12:41,321][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:12:41,830][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:12:42,340][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:12:42,848][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:12:43,357][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:12:43,867][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:12:44,375][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:12:44,883][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:12:45,391][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:12:45,900][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:12:46,409][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:12:46,917][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:12:47,426][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:12:47,935][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:12:48,444][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:12:48,952][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:12:49,459][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:12:49,967][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:12:50,475][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:12:50,982][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:12:51,491][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:12:51,998][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:12:52,506][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:12:53,013][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:12:53,522][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:12:54,030][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:12:54,539][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:12:55,047][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:12:55,555][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:12:56,065][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:12:56,573][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:12:57,082][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:12:57,591][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:12:58,099][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:12:58,609][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:12:59,117][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:12:59,627][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:13:00,136][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:13:00,645][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:13:01,154][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:13:01,665][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:13:02,174][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:13:02,683][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:13:03,192][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:13:03,702][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:13:04,212][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:13:04,722][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:13:05,232][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:13:05,742][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:13:06,252][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:13:06,762][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:13:07,272][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:13:07,781][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:13:08,290][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:13:08,798][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:13:09,307][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:13:09,815][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:13:10,327][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:13:10,838][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:13:11,346][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:13:11,855][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:13:12,365][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:13:12,874][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:13:13,382][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:13:13,891][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:13:14,400][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:13:14,908][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:13:15,416][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:13:15,926][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:13:16,436][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:13:16,944][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:13:17,453][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:13:17,961][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:13:18,470][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21683 tokens. [2026-03-25 23:13:19,139][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:08 [2026-03-25 23:13:19,777][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:13:19,779][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:13:19,781][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:13:20,382][__main__][INFO] - Iteration 349 took 1m 18s (9.29% Gen, 89.94% Train). Generation: 7s, Training: 1m 10s. Estimated remaining time: 57h 43m 37s. Estimated total time: 65h 21m 44s. Time estimates for 10 more iterations: 13m 4s, 100 more iterations: 2h 10m 43s, 500 more iterations: 10h 53m 37s. [2026-03-25 23:13:20,386][__main__][INFO] - Starting iteration 349. [2026-03-25 23:13:20,787][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 23:13:20,788][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:13:26,605][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:13:27,389][__main__][INFO] - Number of regex retries in iteration 349: 1 [2026-03-25 23:13:27,390][__main__][INFO] - agents played in iteration 349 are Bob, Alice [2026-03-25 23:13:28,624][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:13:29,241][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:13:29,706][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:13:30,220][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:13:30,728][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:13:31,237][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:13:31,747][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:13:32,256][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:13:32,763][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:13:33,271][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:13:33,782][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:13:34,291][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:13:34,800][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:13:35,308][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:13:35,816][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:13:36,325][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:13:36,834][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:13:37,346][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:13:37,858][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:13:38,367][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:13:38,877][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:13:39,386][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:13:39,895][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:13:40,405][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:13:40,914][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:13:41,425][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:13:41,933][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:13:42,440][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:13:42,948][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:13:43,457][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:13:43,964][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:13:44,472][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:13:44,980][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:13:45,488][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:13:45,996][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:13:46,504][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:13:47,010][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:13:47,517][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:13:48,027][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:13:48,536][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:13:49,045][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:13:49,554][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:13:50,063][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:13:50,572][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:13:51,080][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:13:51,588][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:13:52,096][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:13:52,607][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:13:53,116][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:13:53,626][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:13:54,134][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:13:54,644][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:13:55,154][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:13:55,661][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:13:56,169][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:13:56,677][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:13:57,185][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:13:57,692][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:13:58,200][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:13:58,708][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:13:59,215][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:13:59,724][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:14:00,232][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:14:00,740][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:14:01,249][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:14:01,756][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:14:02,267][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:14:02,775][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:14:03,283][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:14:03,791][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:14:04,300][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:14:04,809][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:14:05,318][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:14:05,827][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:14:06,336][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:14:06,846][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:14:07,355][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:14:07,866][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:14:08,375][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:14:08,884][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:14:09,393][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:14:09,902][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:14:10,411][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:14:10,920][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:14:11,429][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:14:11,939][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:14:12,449][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:14:12,957][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:14:13,467][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:14:13,976][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:14:14,484][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:14:14,992][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:14:15,500][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:14:16,008][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:14:16,516][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:14:17,025][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:14:17,535][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:14:18,044][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:14:18,552][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:14:19,059][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:14:19,567][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:14:20,075][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:14:20,583][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:14:21,091][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:14:21,599][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:14:22,108][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:14:22,616][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:14:23,126][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:14:23,635][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:14:24,143][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:14:24,652][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:14:25,160][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:14:25,669][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:14:26,178][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:14:26,686][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:14:27,193][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:14:27,701][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:14:28,210][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:14:28,717][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:14:29,225][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:14:29,733][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:14:30,242][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:14:30,749][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:14:31,257][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:14:31,764][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:14:32,272][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:14:32,780][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:14:33,287][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:14:33,794][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:14:34,303][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 23:14:34,968][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 23:14:35,710][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:14:35,712][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:14:35,713][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:14:36,455][__main__][INFO] - Iteration 350 took 1m 15s (8.73% Gen, 90.29% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 24m 3s. Estimated total time: 63h 3m 27s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 6s, 500 more iterations: 10h 30m 34s. [2026-03-25 23:14:36,458][__main__][INFO] - Starting iteration 350. [2026-03-25 23:14:36,862][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 6 and human policies 1. [2026-03-25 23:14:36,863][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:14:40,884][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:14:43,582][__main__][INFO] - Number of regex retries in iteration 350: 1 [2026-03-25 23:14:43,876][__main__][INFO] - agents played in iteration 350 are Bob, Alice [2026-03-25 23:14:44,838][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:14:45,463][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:14:45,929][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:14:46,442][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:14:46,951][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:14:47,459][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:14:47,968][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:14:48,477][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:14:48,985][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:14:49,494][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:14:50,007][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:14:50,518][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:14:51,028][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:14:51,537][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:14:52,046][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:14:52,556][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:14:53,065][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:14:53,575][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:14:54,084][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:14:54,592][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:14:55,100][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:14:55,609][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:14:56,117][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:14:56,626][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:14:57,134][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:14:57,644][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:14:58,152][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:14:58,661][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:14:59,169][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:14:59,677][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:15:00,185][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:15:00,693][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:15:01,202][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:15:01,710][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:15:02,219][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:15:02,727][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:15:03,238][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:15:03,749][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:15:04,259][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:15:04,769][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:15:05,279][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:15:05,788][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:15:06,297][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:15:06,806][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:15:07,315][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:15:07,824][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:15:08,334][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:15:08,843][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:15:09,352][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:15:09,861][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:15:10,368][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:15:10,874][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:15:11,382][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:15:11,889][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:15:12,396][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:15:12,905][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:15:13,412][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:15:13,919][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:15:14,427][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:15:14,935][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:15:15,444][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:15:15,953][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:15:16,463][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:15:16,971][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:15:17,479][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:15:17,987][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:15:18,496][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:15:19,004][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:15:19,514][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:15:20,024][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:15:20,532][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:15:21,041][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:15:21,551][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:15:22,059][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:15:22,569][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:15:23,078][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:15:23,587][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:15:24,096][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:15:24,607][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:15:25,116][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:15:25,627][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:15:26,138][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:15:26,647][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:15:27,155][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:15:27,662][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:15:28,171][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:15:28,679][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:15:29,187][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:15:29,695][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:15:30,205][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:15:30,713][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:15:31,221][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:15:31,731][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:15:32,240][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:15:32,748][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:15:33,258][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:15:33,767][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:15:34,276][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:15:34,784][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:15:35,295][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:15:35,806][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:15:36,316][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:15:36,826][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:15:37,337][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:15:37,847][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:15:38,357][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:15:38,867][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:15:39,376][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:15:39,885][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:15:40,393][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:15:40,903][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:15:41,412][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:15:41,920][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:15:42,429][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:15:42,937][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:15:43,444][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:15:43,951][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:15:44,458][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:15:44,966][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:15:45,473][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:15:45,980][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:15:46,489][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:15:46,997][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:15:47,505][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:15:48,013][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:15:48,523][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:15:49,031][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:15:49,540][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:15:50,048][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:15:50,556][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21733 tokens. [2026-03-25 23:15:51,212][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.36%, ΔTime: 00:01:05 [2026-03-25 23:15:51,957][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:15:51,960][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:15:51,961][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:15:53,199][__main__][INFO] - Iteration 351 took 1m 16s (9.19% Gen, 89.19% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 56m 13s. Estimated total time: 63h 36m 53s. Time estimates for 10 more iterations: 12m 43s, 100 more iterations: 2h 7m 13s, 500 more iterations: 10h 36m 8s. [2026-03-25 23:15:53,201][__main__][INFO] - Starting iteration 351. [2026-03-25 23:15:53,604][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:15:53,604][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:15:54,263][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:16:00,460][__main__][INFO] - Number of regex retries in iteration 351: 1 [2026-03-25 23:16:00,461][__main__][INFO] - agents played in iteration 351 are Bob, Alice [2026-03-25 23:16:01,416][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:16:02,046][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:16:02,510][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:16:03,025][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:16:03,533][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:16:04,041][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:16:04,548][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:16:05,056][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:16:05,564][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:16:06,072][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:16:06,579][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:16:07,086][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:16:07,593][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:16:08,100][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:16:08,607][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:16:09,116][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:16:09,624][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:16:10,131][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:16:10,640][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:16:11,148][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:16:11,655][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:16:12,163][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:16:12,671][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:16:13,178][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:16:13,686][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:16:14,193][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:16:14,702][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:16:15,211][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:16:15,719][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:16:16,230][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:16:16,739][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:16:17,247][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:16:17,755][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:16:18,264][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:16:18,773][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:16:19,281][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:16:19,789][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:16:20,297][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:16:20,806][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:16:21,315][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:16:21,824][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:16:22,333][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:16:22,841][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:16:23,349][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:16:23,858][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:16:24,366][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:16:24,875][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:16:25,382][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:16:25,889][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:16:26,397][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:16:26,907][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:16:27,416][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:16:27,926][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:16:28,435][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:16:28,943][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:16:29,450][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:16:29,957][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:16:30,465][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:16:30,974][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:16:31,483][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:16:31,991][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:16:32,501][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:16:33,009][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:16:33,517][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:16:34,028][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:16:34,538][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:16:35,046][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:16:35,554][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:16:36,063][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:16:36,572][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:16:37,080][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:16:37,589][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:16:38,097][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:16:38,605][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:16:39,112][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:16:39,620][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:16:40,129][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:16:40,637][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:16:41,145][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:16:41,652][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:16:42,161][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:16:42,669][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:16:43,177][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:16:43,686][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:16:44,194][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:16:44,702][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:16:45,210][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:16:45,719][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:16:46,228][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:16:46,736][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:16:47,246][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:16:47,754][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:16:48,263][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:16:48,771][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:16:49,280][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:16:49,789][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:16:50,297][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:16:50,807][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:16:51,316][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:16:51,825][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:16:52,334][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:16:52,842][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:16:53,351][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:16:53,859][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:16:54,367][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:16:54,875][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:16:55,385][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:16:55,892][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:16:56,400][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:16:56,908][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:16:57,416][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:16:57,924][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:16:58,432][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:16:58,941][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:16:59,450][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:16:59,959][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:17:00,468][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:17:00,976][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:17:01,485][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:17:01,994][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:17:02,504][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:17:03,013][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:17:03,522][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:17:04,032][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:17:04,541][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:17:05,050][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:17:05,558][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:17:06,068][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:17:06,576][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:17:07,085][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 23:17:07,746][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-25 23:17:08,490][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:17:08,492][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:17:08,494][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:17:09,272][__main__][INFO] - Iteration 352 took 1m 15s (9.06% Gen, 89.91% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 21m 32s. Estimated total time: 63h 3m 28s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 6s, 500 more iterations: 10h 30m 34s. [2026-03-25 23:17:09,274][__main__][INFO] - Starting iteration 352. [2026-03-25 23:17:09,678][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:17:09,679][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:17:16,142][__main__][INFO] - Number of regex retries in iteration 352: 0 [2026-03-25 23:17:16,143][__main__][INFO] - agents played in iteration 352 are Bob, Alice [2026-03-25 23:17:17,105][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:17:17,731][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:17:18,196][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:17:18,709][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:17:19,217][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:17:19,727][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:17:20,235][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:17:20,744][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:17:21,252][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:17:21,760][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:17:22,268][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:17:22,777][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:17:23,284][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:17:23,792][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:17:24,301][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:17:24,809][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:17:25,317][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:17:25,828][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:17:26,340][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:17:26,850][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:17:27,359][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:17:27,869][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:17:28,377][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:17:28,887][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:17:29,397][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:17:29,906][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:17:30,415][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:17:30,925][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:17:31,433][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:17:31,942][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:17:32,450][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:17:32,958][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:17:33,467][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:17:33,975][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:17:34,485][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:17:34,994][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:17:35,504][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:17:36,013][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:17:36,523][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:17:37,034][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:17:37,544][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:17:38,053][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:17:38,562][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:17:39,071][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:17:39,578][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:17:40,087][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:17:40,594][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:17:41,103][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:17:41,611][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:17:42,118][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:17:42,628][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:17:43,137][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:17:43,645][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:17:44,154][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:17:44,663][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:17:45,171][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:17:45,680][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:17:46,188][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:17:46,697][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:17:47,205][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:17:47,713][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:17:48,222][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:17:48,731][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:17:49,240][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:17:49,749][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:17:50,258][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:17:50,767][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:17:51,275][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:17:51,783][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:17:52,292][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:17:52,801][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:17:53,310][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:17:53,818][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:17:54,327][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:17:54,837][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:17:55,344][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:17:55,852][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:17:56,362][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:17:56,870][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:17:57,377][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:17:57,886][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:17:58,395][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:17:58,904][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:17:59,412][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:17:59,921][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:18:00,431][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:18:00,940][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:18:01,448][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:18:01,956][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:18:02,465][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:18:02,972][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:18:03,481][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:18:03,989][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:18:04,497][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:18:05,006][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:18:05,513][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:18:06,021][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:18:06,530][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:18:07,038][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:18:07,548][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:18:08,059][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:18:08,567][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:18:09,076][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:18:09,586][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:18:10,094][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:18:10,604][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:18:11,112][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:18:11,620][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:18:12,129][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:18:12,638][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:18:13,147][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:18:13,656][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:18:14,164][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:18:14,674][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:18:15,181][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:18:15,689][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:18:16,197][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:18:16,705][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:18:17,212][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:18:17,719][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:18:18,224][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:18:18,732][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:18:19,240][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:18:19,749][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:18:20,257][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:18:20,764][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:18:21,271][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:18:21,778][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:18:22,287][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:18:22,794][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21698 tokens. [2026-03-25 23:18:23,451][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:05 [2026-03-25 23:18:24,196][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:18:24,198][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:18:24,199][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:18:24,801][__main__][INFO] - Iteration 353 took 1m 15s (8.60% Gen, 90.59% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 52m 58s. Estimated total time: 62h 36m 9s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 12s, 500 more iterations: 10h 26m 1s. [2026-03-25 23:18:24,804][__main__][INFO] - Starting iteration 353. [2026-03-25 23:18:25,204][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:18:25,205][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:18:31,845][__main__][INFO] - Number of regex retries in iteration 353: 0 [2026-03-25 23:18:31,847][__main__][INFO] - agents played in iteration 353 are Bob, Alice [2026-03-25 23:18:33,097][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:18:33,720][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:18:34,185][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:18:34,698][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:18:35,207][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:18:35,716][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:18:36,225][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:18:36,736][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:18:37,246][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:18:37,755][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:18:38,262][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:18:38,771][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:18:39,280][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:18:39,789][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:18:40,297][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:18:40,807][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:18:41,316][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:18:41,825][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:18:42,334][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:18:42,843][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:18:43,351][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:18:43,860][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:18:44,368][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:18:44,877][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:18:45,387][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:18:45,894][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:18:46,404][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:18:46,912][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:18:47,418][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:18:47,926][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:18:48,434][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:18:48,942][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:18:49,449][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:18:49,956][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:18:50,467][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:18:50,975][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:18:51,483][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:18:51,990][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:18:52,500][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:18:53,008][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:18:53,514][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:18:54,024][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:18:54,533][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:18:55,040][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:18:55,548][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:18:56,056][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:18:56,564][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:18:57,071][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:18:57,579][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:18:58,087][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:18:58,595][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:18:59,102][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:18:59,610][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:19:00,117][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:19:00,626][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:19:01,134][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:19:01,641][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:19:02,150][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:19:02,658][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:19:03,165][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:19:03,673][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:19:04,181][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:19:04,689][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:19:05,196][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:19:05,705][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:19:06,215][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:19:06,726][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:19:07,235][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:19:07,745][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:19:08,255][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:19:08,764][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:19:09,273][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:19:09,782][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:19:10,291][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:19:10,800][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:19:11,309][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:19:11,818][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:19:12,328][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:19:12,836][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:19:13,347][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:19:13,856][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:19:14,364][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:19:14,873][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:19:15,382][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:19:15,891][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:19:16,399][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:19:16,909][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:19:17,417][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:19:17,927][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:19:18,436][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:19:18,946][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:19:19,455][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:19:19,963][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:19:20,472][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:19:20,980][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:19:21,488][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:19:21,997][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:19:22,505][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:19:23,013][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:19:23,520][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:19:24,029][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:19:24,539][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:19:25,047][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:19:25,556][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:19:26,063][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:19:26,572][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:19:27,078][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:19:27,585][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:19:28,092][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:19:28,598][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:19:29,106][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:19:29,613][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:19:30,120][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:19:30,626][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:19:31,135][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:19:31,643][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:19:32,150][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:19:32,657][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:19:33,166][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:19:33,673][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:19:34,180][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:19:34,689][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:19:35,196][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:19:35,704][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:19:36,211][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:19:36,719][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:19:37,228][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:19:37,736][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:19:38,245][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:19:38,752][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21747 tokens. [2026-03-25 23:19:39,416][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-25 23:19:40,159][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:19:40,161][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:19:40,163][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:19:40,933][__main__][INFO] - Iteration 354 took 1m 15s (8.77% Gen, 90.21% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 22m 1s. Estimated total time: 63h 6m 29s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 12s, 500 more iterations: 10h 31m 4s. [2026-03-25 23:19:40,935][__main__][INFO] - Starting iteration 354. [2026-03-25 23:19:41,347][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:19:41,348][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:19:48,282][__main__][INFO] - Number of regex retries in iteration 354: 0 [2026-03-25 23:19:48,283][__main__][INFO] - agents played in iteration 354 are Bob, Alice [2026-03-25 23:19:49,287][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:19:49,917][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:19:50,423][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:19:50,941][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:19:51,449][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:19:51,959][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:19:52,468][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:19:52,976][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:19:53,484][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:19:53,993][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:19:54,499][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:19:55,007][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:19:55,514][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:19:56,022][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:19:56,529][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:19:57,038][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:19:57,546][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:19:58,054][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:19:58,567][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:19:59,079][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:19:59,590][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:20:00,100][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:20:00,612][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:20:01,123][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:20:01,634][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:20:02,146][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:20:02,655][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:20:03,163][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:20:03,672][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:20:04,180][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:20:04,689][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:20:05,196][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:20:05,706][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:20:06,215][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:20:06,723][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:20:07,231][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:20:07,739][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:20:08,247][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:20:08,755][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:20:09,262][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:20:09,770][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:20:10,278][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:20:10,788][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:20:11,296][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:20:11,807][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:20:12,317][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:20:12,827][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:20:13,337][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:20:13,848][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:20:14,358][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:20:14,866][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:20:15,375][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:20:15,884][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:20:16,393][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:20:16,902][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:20:17,410][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:20:17,918][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:20:18,428][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:20:18,937][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:20:19,447][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:20:19,956][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:20:20,465][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:20:20,974][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:20:21,483][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:20:21,992][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:20:22,500][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:20:23,009][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:20:23,517][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:20:24,027][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:20:24,537][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:20:25,046][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:20:25,555][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:20:26,064][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:20:26,573][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:20:27,082][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:20:27,590][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:20:28,098][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:20:28,608][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:20:29,116][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:20:29,626][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:20:30,136][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:20:30,647][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:20:31,158][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:20:31,669][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:20:32,181][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:20:32,693][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:20:33,204][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:20:33,714][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:20:34,227][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:20:34,738][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:20:35,248][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:20:35,757][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:20:36,265][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:20:36,774][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:20:37,283][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:20:37,792][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:20:38,300][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:20:38,808][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:20:39,315][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:20:39,823][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:20:40,331][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:20:40,839][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:20:41,347][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:20:41,855][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:20:42,362][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:20:42,870][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:20:43,378][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:20:43,887][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:20:44,395][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:20:44,907][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:20:45,417][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:20:45,928][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:20:46,438][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:20:46,949][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:20:47,458][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:20:47,967][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:20:48,476][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:20:48,986][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:20:49,496][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:20:50,007][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:20:50,516][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:20:51,025][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:20:51,535][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:20:52,047][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:20:52,555][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:20:53,065][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:20:53,574][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:20:54,084][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:20:54,593][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:20:55,102][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 23:20:55,766][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.28%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:05 [2026-03-25 23:20:56,517][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:20:56,519][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:20:56,521][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:20:57,180][__main__][INFO] - Iteration 355 took 1m 15s (9.14% Gen, 89.98% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 25m 57s. Estimated total time: 63h 11m 40s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 23s, 500 more iterations: 10h 31m 56s. [2026-03-25 23:20:57,182][__main__][INFO] - Starting iteration 355. [2026-03-25 23:20:57,584][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:20:57,585][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:21:04,110][__main__][INFO] - Number of regex retries in iteration 355: 0 [2026-03-25 23:21:04,112][__main__][INFO] - agents played in iteration 355 are Bob, Alice [2026-03-25 23:21:05,364][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:21:05,984][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:21:06,450][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:21:06,966][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:21:07,475][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:21:07,984][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:21:08,493][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:21:09,001][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:21:09,511][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:21:10,020][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:21:10,530][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:21:11,039][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:21:11,549][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:21:12,058][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:21:12,567][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:21:13,076][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:21:13,584][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:21:14,093][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:21:14,603][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:21:15,111][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:21:15,619][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:21:16,129][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:21:16,640][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:21:17,148][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:21:17,657][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:21:18,167][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:21:18,676][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:21:19,184][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:21:19,692][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:21:20,201][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:21:20,710][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:21:21,218][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:21:21,727][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:21:22,236][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:21:22,745][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:21:23,253][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:21:23,762][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:21:24,270][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:21:24,779][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:21:25,288][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:21:25,797][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:21:26,305][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:21:26,814][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:21:27,327][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:21:27,837][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:21:28,347][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:21:28,857][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:21:29,367][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:21:29,876][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:21:30,386][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:21:30,894][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:21:31,402][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:21:31,909][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:21:32,416][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:21:32,927][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:21:33,436][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:21:33,944][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:21:34,453][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:21:34,961][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:21:35,470][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:21:35,980][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:21:36,491][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:21:36,999][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:21:37,507][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:21:38,016][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:21:38,527][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:21:39,037][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:21:39,546][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:21:40,055][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:21:40,566][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:21:41,075][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:21:41,585][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:21:42,093][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:21:42,603][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:21:43,111][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:21:43,619][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:21:44,129][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:21:44,638][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:21:45,146][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:21:45,655][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:21:46,165][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:21:46,673][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:21:47,182][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:21:47,690][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:21:48,200][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:21:48,708][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:21:49,216][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:21:49,728][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:21:50,237][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:21:50,746][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:21:51,255][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:21:51,765][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:21:52,273][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:21:52,781][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:21:53,289][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:21:53,797][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:21:54,305][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:21:54,813][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:21:55,322][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:21:55,830][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:21:56,338][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:21:56,846][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:21:57,354][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:21:57,863][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:21:58,371][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:21:58,879][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:21:59,388][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:21:59,897][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:22:00,406][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:22:00,916][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:22:01,426][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:22:01,935][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:22:02,444][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:22:02,953][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:22:03,461][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:22:03,970][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:22:04,478][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:22:04,988][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:22:05,497][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:22:06,005][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:22:06,513][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:22:07,023][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:22:07,532][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:22:08,040][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:22:08,549][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:22:09,058][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:22:09,567][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:22:10,076][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:22:10,586][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:22:11,095][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 23:22:11,745][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-25 23:22:12,491][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:22:12,493][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:22:12,495][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:22:13,148][__main__][INFO] - Iteration 356 took 1m 15s (8.64% Gen, 90.50% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 11m 14s. Estimated total time: 62h 58m 14s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 56s, 500 more iterations: 10h 29m 42s. [2026-03-25 23:22:13,150][__main__][INFO] - Starting iteration 356. [2026-03-25 23:22:13,551][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:22:13,552][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:22:19,396][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:22:20,474][__main__][INFO] - Number of regex retries in iteration 356: 1 [2026-03-25 23:22:20,474][__main__][INFO] - agents played in iteration 356 are Bob, Alice [2026-03-25 23:22:21,441][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:22:22,064][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:22:22,529][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:22:23,045][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:22:23,554][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:22:24,063][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:22:24,572][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:22:25,080][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:22:25,589][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:22:26,099][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:22:26,607][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:22:27,116][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:22:27,624][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:22:28,133][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:22:28,642][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:22:29,151][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:22:29,659][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:22:30,168][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:22:30,675][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:22:31,184][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:22:31,692][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:22:32,200][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:22:32,708][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:22:33,218][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:22:33,725][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:22:34,231][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:22:34,739][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:22:35,249][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:22:35,758][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:22:36,266][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:22:36,775][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:22:37,283][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:22:37,792][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:22:38,299][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:22:38,808][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:22:39,316][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:22:39,825][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:22:40,333][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:22:40,841][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:22:41,350][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:22:41,857][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:22:42,367][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:22:42,875][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:22:43,383][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:22:43,890][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:22:44,399][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:22:44,908][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:22:45,416][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:22:45,925][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:22:46,433][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:22:46,941][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:22:47,449][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:22:47,956][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:22:48,465][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:22:48,973][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:22:49,481][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:22:49,988][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:22:50,495][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:22:51,004][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:22:51,511][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:22:52,018][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:22:52,526][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:22:53,033][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:22:53,540][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:22:54,047][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:22:54,554][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:22:55,064][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:22:55,572][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:22:56,079][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:22:56,588][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:22:57,095][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:22:57,603][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:22:58,111][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:22:58,618][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:22:59,126][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:22:59,634][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:23:00,141][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:23:00,647][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:23:01,157][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:23:01,667][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:23:02,176][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:23:02,685][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:23:03,194][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:23:03,702][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:23:04,210][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:23:04,718][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:23:05,226][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:23:05,735][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:23:06,245][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:23:06,753][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:23:07,261][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:23:07,770][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:23:08,278][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:23:08,787][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:23:09,294][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:23:09,803][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:23:10,312][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:23:10,819][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:23:11,329][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:23:11,837][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:23:12,347][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:23:12,855][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:23:13,363][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:23:13,871][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:23:14,379][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:23:14,888][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:23:15,396][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:23:15,904][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:23:16,411][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:23:16,919][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:23:17,427][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:23:17,935][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:23:18,443][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:23:18,950][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:23:19,458][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:23:19,966][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:23:20,475][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:23:20,983][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:23:21,491][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:23:22,000][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:23:22,509][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:23:23,017][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:23:23,527][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:23:24,036][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:23:24,543][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:23:25,050][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:23:25,558][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:23:26,066][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:23:26,573][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:23:27,079][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 23:23:27,728][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-25 23:23:28,478][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:23:28,481][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:23:28,482][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:23:29,141][__main__][INFO] - Iteration 357 took 1m 15s (9.16% Gen, 89.97% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 11m 15s. Estimated total time: 62h 59m 30s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 59s, 500 more iterations: 10h 29m 55s. [2026-03-25 23:23:29,143][__main__][INFO] - Starting iteration 357. [2026-03-25 23:23:29,557][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:23:29,557][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:23:37,091][__main__][INFO] - Number of regex retries in iteration 357: 0 [2026-03-25 23:23:37,092][__main__][INFO] - agents played in iteration 357 are Bob, Alice [2026-03-25 23:23:38,199][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:23:38,828][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:23:39,293][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:23:39,806][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:23:40,313][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:23:40,821][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:23:41,329][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:23:41,837][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:23:42,346][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:23:42,853][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:23:43,360][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:23:43,871][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:23:44,378][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:23:44,888][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:23:45,398][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:23:45,906][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:23:46,417][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:23:46,927][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:23:47,435][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:23:47,944][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:23:48,452][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:23:48,961][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:23:49,468][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:23:49,975][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:23:50,483][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:23:50,990][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:23:51,502][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:23:52,011][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:23:52,523][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:23:53,033][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:23:53,543][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:23:54,054][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:23:54,564][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:23:55,074][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:23:55,584][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:23:56,093][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:23:56,602][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:23:57,112][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:23:57,622][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:23:58,132][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:23:58,641][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:23:59,151][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:23:59,658][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:24:00,166][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:24:00,674][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:24:01,183][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:24:01,691][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:24:02,198][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:24:02,708][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:24:03,215][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:24:03,725][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:24:04,234][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:24:04,744][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:24:05,252][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:24:05,762][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:24:06,270][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:24:06,778][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:24:07,288][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:24:07,795][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:24:08,303][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:24:08,811][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:24:09,319][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:24:09,827][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:24:10,335][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:24:10,845][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:24:11,354][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:24:11,862][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:24:12,371][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:24:12,879][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:24:13,387][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:24:13,895][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:24:14,402][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:24:14,911][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:24:15,420][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:24:15,928][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:24:16,437][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:24:16,947][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:24:17,457][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:24:17,966][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:24:18,475][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:24:18,984][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:24:19,493][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:24:20,000][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:24:20,510][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:24:21,017][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:24:21,524][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:24:22,032][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:24:22,540][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:24:23,048][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:24:23,555][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:24:24,067][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:24:24,577][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:24:25,086][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:24:25,596][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:24:26,107][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:24:26,617][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:24:27,129][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:24:27,639][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:24:28,148][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:24:28,657][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:24:29,167][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:24:29,676][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:24:30,185][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:24:30,695][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:24:31,205][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:24:31,714][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:24:32,222][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:24:32,731][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:24:33,238][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:24:33,747][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:24:34,255][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:24:34,763][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:24:35,271][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:24:35,779][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:24:36,287][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:24:36,794][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:24:37,304][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:24:37,811][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:24:38,320][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:24:38,829][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:24:39,338][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:24:39,846][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:24:40,356][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:24:40,864][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:24:41,373][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:24:41,882][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:24:42,391][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:24:42,898][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:24:43,407][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:24:43,916][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21702 tokens. [2026-03-25 23:24:44,577][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-25 23:24:45,327][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:24:45,329][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:24:45,331][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:24:45,977][__main__][INFO] - Iteration 358 took 1m 16s (9.86% Gen, 89.29% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 51m 29s. Estimated total time: 63h 41m 1s. Time estimates for 10 more iterations: 12m 44s, 100 more iterations: 2h 7m 22s, 500 more iterations: 10h 36m 50s. [2026-03-25 23:24:45,979][__main__][INFO] - Starting iteration 358. [2026-03-25 23:24:46,383][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:24:46,384][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:24:53,337][__main__][INFO] - Number of regex retries in iteration 358: 0 [2026-03-25 23:24:53,338][__main__][INFO] - agents played in iteration 358 are Bob, Alice [2026-03-25 23:24:54,292][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:24:54,922][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:24:55,390][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:24:55,906][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:24:56,415][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:24:56,926][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:24:57,437][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:24:57,947][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:24:58,456][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:24:58,966][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:24:59,475][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:24:59,984][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:25:00,492][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:25:01,000][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:25:01,510][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:25:02,018][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:25:02,527][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:25:03,036][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:25:03,549][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:25:04,059][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:25:04,569][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:25:05,080][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:25:05,590][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:25:06,100][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:25:06,611][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:25:07,122][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:25:07,633][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:25:08,143][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:25:08,653][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:25:09,163][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:25:09,673][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:25:10,181][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:25:10,690][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:25:11,200][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:25:11,709][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:25:12,218][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:25:12,730][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:25:13,241][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:25:13,750][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:25:14,259][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:25:14,768][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:25:15,277][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:25:15,787][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:25:16,296][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:25:16,805][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:25:17,315][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:25:17,825][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:25:18,335][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:25:18,845][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:25:19,354][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:25:19,864][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:25:20,376][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:25:20,887][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:25:21,396][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:25:21,907][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:25:22,417][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:25:22,929][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:25:23,439][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:25:23,949][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:25:24,459][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:25:24,969][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:25:25,478][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:25:25,987][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:25:26,496][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:25:27,008][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:25:27,518][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:25:28,028][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:25:28,538][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:25:29,048][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:25:29,558][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:25:30,069][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:25:30,579][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:25:31,088][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:25:31,598][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:25:32,107][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:25:32,615][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:25:33,125][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:25:33,633][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:25:34,141][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:25:34,650][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:25:35,158][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:25:35,667][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:25:36,176][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:25:36,685][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:25:37,195][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:25:37,705][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:25:38,215][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:25:38,725][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:25:39,233][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:25:39,741][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:25:40,251][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:25:40,760][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:25:41,270][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:25:41,779][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:25:42,289][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:25:42,798][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:25:43,307][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:25:43,816][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:25:44,326][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:25:44,836][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:25:45,347][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:25:45,857][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:25:46,367][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:25:46,876][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:25:47,386][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:25:47,895][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:25:48,404][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:25:48,913][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:25:49,421][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:25:49,931][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:25:50,440][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:25:50,950][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:25:51,459][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:25:51,968][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:25:52,477][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:25:52,988][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:25:53,498][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:25:54,007][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:25:54,518][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:25:55,028][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:25:55,538][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:25:56,049][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:25:56,558][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:25:57,067][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:25:57,577][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:25:58,088][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:25:58,597][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:25:59,106][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:25:59,615][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:26:00,126][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 23:26:00,785][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 23:26:01,537][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:26:01,539][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:26:01,540][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:26:02,279][__main__][INFO] - Iteration 359 took 1m 15s (9.16% Gen, 89.86% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 24m 3s. Estimated total time: 63h 14m 52s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 29s, 500 more iterations: 10h 32m 28s. [2026-03-25 23:26:02,282][__main__][INFO] - Starting iteration 359. [2026-03-25 23:26:02,685][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:26:02,685][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:26:03,322][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:26:09,310][__main__][INFO] - Number of regex retries in iteration 359: 1 [2026-03-25 23:26:09,311][__main__][INFO] - agents played in iteration 359 are Bob, Alice [2026-03-25 23:26:10,268][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:26:10,901][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:26:11,368][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:26:11,882][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:26:12,392][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:26:12,901][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:26:13,409][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:26:13,918][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:26:14,427][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:26:14,936][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:26:15,450][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:26:15,962][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:26:16,473][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:26:16,984][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:26:17,496][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:26:18,007][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:26:18,518][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:26:19,029][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:26:19,539][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:26:20,048][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:26:20,557][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:26:21,066][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:26:21,575][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:26:22,083][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:26:22,592][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:26:23,101][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:26:23,611][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:26:24,120][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:26:24,629][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:26:25,138][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:26:25,646][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:26:26,155][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:26:26,665][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:26:27,174][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:26:27,684][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:26:28,193][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:26:28,702][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:26:29,212][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:26:29,721][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:26:30,231][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:26:30,741][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:26:31,251][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:26:31,761][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:26:32,271][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:26:32,781][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:26:33,291][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:26:33,801][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:26:34,311][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:26:34,821][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:26:35,332][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:26:35,843][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:26:36,352][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:26:36,863][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:26:37,372][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:26:37,880][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:26:38,390][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:26:38,899][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:26:39,408][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:26:39,917][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:26:40,428][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:26:40,938][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:26:41,448][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:26:41,956][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:26:42,467][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:26:42,976][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:26:43,485][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:26:43,995][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:26:44,504][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:26:45,013][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:26:45,521][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:26:46,029][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:26:46,537][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:26:47,046][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:26:47,555][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:26:48,066][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:26:48,576][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:26:49,086][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:26:49,595][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:26:50,105][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:26:50,615][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:26:51,125][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:26:51,635][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:26:52,146][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:26:52,656][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:26:53,165][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:26:53,675][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:26:54,184][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:26:54,693][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:26:55,202][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:26:55,712][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:26:56,221][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:26:56,730][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:26:57,240][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:26:57,750][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:26:58,259][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:26:58,768][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:26:59,277][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:26:59,785][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:27:00,294][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:27:00,807][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:27:01,318][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:27:01,829][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:27:02,338][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:27:02,848][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:27:03,358][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:27:03,867][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:27:04,377][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:27:04,888][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:27:05,398][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:27:05,908][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:27:06,418][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:27:06,928][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:27:07,437][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:27:07,948][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:27:08,458][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:27:08,967][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:27:09,475][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:27:09,984][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:27:10,493][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:27:11,001][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:27:11,510][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:27:12,019][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:27:12,528][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:27:13,038][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:27:13,549][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:27:14,059][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:27:14,568][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:27:15,077][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:27:15,588][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:27:16,097][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21760 tokens. [2026-03-25 23:27:16,758][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 23:27:17,494][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:27:17,496][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:27:17,498][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:27:18,230][__main__][INFO] - Iteration 360 took 1m 15s (8.77% Gen, 90.26% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 5m 13s. Estimated total time: 62h 57m 18s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 54s, 500 more iterations: 10h 29m 33s. [2026-03-25 23:27:18,232][__main__][INFO] - Starting iteration 360. [2026-03-25 23:27:18,632][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:27:18,633][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:27:25,739][__main__][INFO] - Number of regex retries in iteration 360: 0 [2026-03-25 23:27:25,740][__main__][INFO] - agents played in iteration 360 are Bob, Alice [2026-03-25 23:27:26,692][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:27:27,318][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:27:27,782][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:27:28,294][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:27:28,802][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:27:29,308][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:27:29,816][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:27:30,326][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:27:30,835][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:27:31,343][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:27:31,851][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:27:32,359][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:27:32,869][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:27:33,378][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:27:33,887][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:27:34,394][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:27:34,902][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:27:35,410][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:27:35,916][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:27:36,425][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:27:36,932][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:27:37,440][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:27:37,948][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:27:38,455][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:27:38,963][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:27:39,470][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:27:39,980][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:27:40,487][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:27:40,994][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:27:41,501][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:27:42,009][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:27:42,516][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:27:43,024][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:27:43,533][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:27:44,041][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:27:44,549][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:27:45,057][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:27:45,564][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:27:46,072][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:27:46,579][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:27:47,088][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:27:47,595][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:27:48,106][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:27:48,615][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:27:49,125][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:27:49,633][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:27:50,141][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:27:50,650][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:27:51,159][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:27:51,668][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:27:52,175][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:27:52,681][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:27:53,189][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:27:53,697][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:27:54,204][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:27:54,711][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:27:55,218][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:27:55,726][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:27:56,240][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:27:56,750][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:27:57,259][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:27:57,770][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:27:58,279][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:27:58,788][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:27:59,299][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:27:59,809][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:28:00,317][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:28:00,825][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:28:01,333][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:28:01,840][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:28:02,348][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:28:02,857][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:28:03,366][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:28:03,873][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:28:04,381][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:28:04,889][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:28:05,397][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:28:05,907][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:28:06,416][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:28:06,925][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:28:07,432][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:28:07,941][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:28:08,449][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:28:08,956][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:28:09,463][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:28:09,970][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:28:10,478][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:28:10,984][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:28:11,491][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:28:11,998][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:28:12,506][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:28:13,013][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:28:13,519][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:28:14,028][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:28:14,536][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:28:15,042][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:28:15,549][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:28:16,056][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:28:16,564][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:28:17,072][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:28:17,579][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:28:18,088][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:28:18,595][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:28:19,102][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:28:19,610][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:28:20,118][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:28:20,627][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:28:21,136][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:28:21,645][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:28:22,154][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:28:22,662][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:28:23,170][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:28:23,678][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:28:24,188][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:28:24,695][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:28:25,201][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:28:25,708][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:28:26,215][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:28:26,722][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:28:27,229][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:28:27,736][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:28:28,245][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:28:28,755][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:28:29,266][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:28:29,776][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:28:30,288][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:28:30,799][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:28:31,309][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:28:31,819][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:28:32,330][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-25 23:28:33,001][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.32%, Current % of VRAM taken: 60.67%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-25 23:28:33,752][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:28:33,754][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:28:33,756][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:28:34,505][__main__][INFO] - Iteration 361 took 1m 15s (9.37% Gen, 89.64% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 20m 19s. Estimated total time: 63h 13m 40s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 27s, 500 more iterations: 10h 32m 16s. [2026-03-25 23:28:34,507][__main__][INFO] - Starting iteration 361. [2026-03-25 23:28:34,911][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:28:34,912][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:28:37,099][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:28:41,512][__main__][INFO] - Number of regex retries in iteration 361: 1 [2026-03-25 23:28:41,513][__main__][INFO] - agents played in iteration 361 are Bob, Alice [2026-03-25 23:28:42,596][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:28:43,228][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:28:43,694][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:28:44,209][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:28:44,717][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:28:45,227][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:28:45,737][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:28:46,246][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:28:46,756][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:28:47,264][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:28:47,772][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:28:48,280][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:28:48,789][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:28:49,297][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:28:49,805][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:28:50,313][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:28:50,820][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:28:51,328][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:28:51,838][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:28:52,346][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:28:52,854][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:28:53,363][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:28:53,872][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:28:54,380][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:28:54,887][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:28:55,395][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:28:55,903][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:28:56,411][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:28:56,917][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:28:57,428][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:28:57,936][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:28:58,444][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:28:58,951][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:28:59,459][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:28:59,970][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:29:00,480][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:29:00,990][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:29:01,499][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:29:02,009][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:29:02,518][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:29:03,029][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:29:03,540][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:29:04,048][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:29:04,556][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:29:05,065][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:29:05,574][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:29:06,082][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:29:06,589][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:29:07,097][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:29:07,605][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:29:08,112][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:29:08,619][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:29:09,127][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:29:09,635][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:29:10,142][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:29:10,649][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:29:11,154][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:29:11,661][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:29:12,168][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:29:12,676][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:29:13,184][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:29:13,693][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:29:14,201][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:29:14,710][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:29:15,218][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:29:15,726][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:29:16,236][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:29:16,747][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:29:17,256][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:29:17,765][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:29:18,274][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:29:18,783][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:29:19,293][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:29:19,801][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:29:20,309][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:29:20,818][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:29:21,326][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:29:21,835][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:29:22,344][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:29:22,851][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:29:23,359][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:29:23,868][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:29:24,377][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:29:24,886][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:29:25,394][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:29:25,902][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:29:26,412][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:29:26,922][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:29:27,431][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:29:27,939][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:29:28,447][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:29:28,955][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:29:29,462][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:29:29,970][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:29:30,476][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:29:30,984][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:29:31,491][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:29:31,997][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:29:32,507][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:29:33,016][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:29:33,526][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:29:34,036][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:29:34,547][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:29:35,057][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:29:35,567][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:29:36,077][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:29:36,585][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:29:37,093][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:29:37,601][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:29:38,109][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:29:38,618][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:29:39,126][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:29:39,636][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:29:40,145][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:29:40,653][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:29:41,161][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:29:41,669][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:29:42,177][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:29:42,684][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:29:43,192][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:29:43,699][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:29:44,207][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:29:44,716][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:29:45,225][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:29:45,733][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:29:46,242][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:29:46,750][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:29:47,258][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:29:47,766][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:29:48,275][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 23:29:48,939][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.36%, ΔTime: 00:01:05 [2026-03-25 23:29:49,692][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:29:49,695][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:29:49,696][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:29:50,363][__main__][INFO] - Iteration 362 took 1m 15s (8.75% Gen, 90.37% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 58m 0s. Estimated total time: 62h 52m 37s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 45s, 500 more iterations: 10h 28m 46s. [2026-03-25 23:29:50,365][__main__][INFO] - Starting iteration 362. [2026-03-25 23:29:50,768][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:29:50,769][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:29:57,395][__main__][INFO] - Number of regex retries in iteration 362: 0 [2026-03-25 23:29:57,396][__main__][INFO] - agents played in iteration 362 are Bob, Alice [2026-03-25 23:29:58,352][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:29:58,980][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:29:59,446][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:29:59,961][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:30:00,470][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:30:00,979][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:30:01,488][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:30:01,997][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:30:02,506][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:30:03,015][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:30:03,524][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:30:04,032][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:30:04,542][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:30:05,051][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:30:05,560][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:30:06,068][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:30:06,576][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:30:07,086][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:30:07,594][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:30:08,101][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:30:08,610][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:30:09,118][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:30:09,627][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:30:10,135][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:30:10,646][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:30:11,154][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:30:11,662][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:30:12,170][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:30:12,678][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:30:13,187][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:30:13,695][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:30:14,202][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:30:14,711][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:30:15,220][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:30:15,732][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:30:16,243][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:30:16,754][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:30:17,264][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:30:17,773][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:30:18,283][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:30:18,792][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:30:19,302][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:30:19,811][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:30:20,319][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:30:20,828][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:30:21,337][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:30:21,848][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:30:22,357][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:30:22,865][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:30:23,374][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:30:23,884][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:30:24,393][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:30:24,902][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:30:25,412][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:30:25,922][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:30:26,431][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:30:26,939][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:30:27,450][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:30:27,959][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:30:28,467][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:30:28,976][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:30:29,487][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:30:29,995][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:30:30,504][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:30:31,013][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:30:31,522][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:30:32,030][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:30:32,539][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:30:33,049][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:30:33,558][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:30:34,067][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:30:34,575][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:30:35,086][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:30:35,593][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:30:36,102][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:30:36,611][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:30:37,119][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:30:37,628][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:30:38,138][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:30:38,648][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:30:39,156][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:30:39,665][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:30:40,173][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:30:40,681][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:30:41,190][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:30:41,698][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:30:42,208][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:30:42,717][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:30:43,226][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:30:43,735][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:30:44,243][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:30:44,750][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:30:45,258][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:30:45,767][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:30:46,274][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:30:46,782][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:30:47,289][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:30:47,797][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:30:48,308][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:30:48,818][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:30:49,329][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:30:49,839][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:30:50,349][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:30:50,858][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:30:51,369][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:30:51,880][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:30:52,389][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:30:52,898][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:30:53,408][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:30:53,918][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:30:54,427][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:30:54,937][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:30:55,446][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:30:55,955][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:30:56,464][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:30:56,973][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:30:57,482][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:30:57,991][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:30:58,499][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:30:59,008][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:30:59,518][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:31:00,028][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:31:00,538][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:31:01,048][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:31:01,559][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:31:02,068][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:31:02,577][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:31:03,086][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:31:03,595][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:31:04,105][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 23:31:04,771][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 23:31:05,516][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:31:05,519][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:31:05,520][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:31:06,226][__main__][INFO] - Iteration 363 took 1m 15s (8.78% Gen, 90.28% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 57m 1s. Estimated total time: 62h 52m 54s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 45s, 500 more iterations: 10h 28m 49s. [2026-03-25 23:31:06,228][__main__][INFO] - Starting iteration 363. [2026-03-25 23:31:06,629][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:31:06,630][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:31:07,277][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:31:07,279][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:31:13,973][__main__][INFO] - Number of regex retries in iteration 363: 2 [2026-03-25 23:31:13,973][__main__][INFO] - agents played in iteration 363 are Bob, Alice [2026-03-25 23:31:14,927][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:31:15,559][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:31:16,025][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:31:16,540][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:31:17,049][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:31:17,559][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:31:18,068][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:31:18,577][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:31:19,085][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:31:19,595][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:31:20,102][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:31:20,610][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:31:21,117][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:31:21,628][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:31:22,137][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:31:22,645][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:31:23,155][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:31:23,665][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:31:24,176][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:31:24,685][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:31:25,194][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:31:25,703][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:31:26,213][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:31:26,722][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:31:27,232][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:31:27,742][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:31:28,254][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:31:28,764][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:31:29,274][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:31:29,783][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:31:30,292][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:31:30,802][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:31:31,312][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:31:31,822][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:31:32,330][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:31:32,838][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:31:33,347][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:31:33,856][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:31:34,364][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:31:34,872][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:31:35,380][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:31:35,888][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:31:36,396][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:31:36,905][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:31:37,413][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:31:37,921][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:31:38,430][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:31:38,939][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:31:39,448][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:31:39,956][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:31:40,466][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:31:40,975][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:31:41,483][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:31:41,991][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:31:42,500][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:31:43,009][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:31:43,518][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:31:44,028][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:31:44,537][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:31:45,045][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:31:45,554][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:31:46,063][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:31:46,570][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:31:47,078][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:31:47,587][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:31:48,095][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:31:48,603][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:31:49,112][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:31:49,621][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:31:50,130][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:31:50,640][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:31:51,149][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:31:51,658][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:31:52,168][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:31:52,676][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:31:53,183][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:31:53,691][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:31:54,198][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:31:54,706][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:31:55,213][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:31:55,722][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:31:56,230][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:31:56,739][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:31:57,248][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:31:57,756][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:31:58,266][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:31:58,775][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:31:59,286][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:31:59,795][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:32:00,303][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:32:00,812][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:32:01,322][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:32:01,832][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:32:02,342][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:32:02,850][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:32:03,359][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:32:03,868][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:32:04,378][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:32:04,887][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:32:05,395][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:32:05,903][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:32:06,412][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:32:06,922][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:32:07,433][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:32:07,942][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:32:08,451][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:32:08,962][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:32:09,471][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:32:09,981][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:32:10,491][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:32:11,000][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:32:11,511][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:32:12,021][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:32:12,532][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:32:13,043][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:32:13,555][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:32:14,067][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:32:14,577][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:32:15,086][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:32:15,595][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:32:16,105][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:32:16,614][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:32:17,123][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:32:17,633][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:32:18,142][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:32:18,650][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:32:19,158][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:32:19,668][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:32:20,176][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:32:20,685][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 23:32:21,345][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:05 [2026-03-25 23:32:22,094][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:32:22,096][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:32:22,098][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:32:22,914][__main__][INFO] - Iteration 364 took 1m 16s (9.63% Gen, 89.30% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 37m 9s. Estimated total time: 63h 34m 18s. Time estimates for 10 more iterations: 12m 42s, 100 more iterations: 2h 7m 8s, 500 more iterations: 10h 35m 43s. [2026-03-25 23:32:22,917][__main__][INFO] - Starting iteration 364. [2026-03-25 23:32:23,329][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:32:23,329][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:32:26,771][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:32:26,864][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:32:27,634][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:32:31,539][__main__][INFO] - Number of regex retries in iteration 364: 3 [2026-03-25 23:32:31,540][__main__][INFO] - agents played in iteration 364 are Bob, Alice [2026-03-25 23:32:32,676][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:32:33,304][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:32:33,768][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:32:34,281][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:32:34,788][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:32:35,296][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:32:35,805][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:32:36,313][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:32:36,821][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:32:37,330][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:32:37,838][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:32:38,349][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:32:38,858][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:32:39,366][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:32:39,874][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:32:40,382][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:32:40,890][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:32:41,399][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:32:41,908][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:32:42,417][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:32:42,927][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:32:43,436][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:32:43,948][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:32:44,457][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:32:44,966][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:32:45,476][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:32:45,987][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:32:46,496][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:32:47,006][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:32:47,515][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:32:48,025][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:32:48,535][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:32:49,045][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:32:49,554][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:32:50,067][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:32:50,577][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:32:51,087][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:32:51,597][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:32:52,106][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:32:52,616][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:32:53,126][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:32:53,636][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:32:54,144][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:32:54,652][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:32:55,160][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:32:55,669][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:32:56,177][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:32:56,686][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:32:57,195][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:32:57,703][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:32:58,210][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:32:58,718][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:32:59,227][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:32:59,736][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:33:00,246][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:33:00,754][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:33:01,263][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:33:01,771][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:33:02,280][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:33:02,790][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:33:03,298][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:33:03,809][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:33:04,318][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:33:04,827][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:33:05,337][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:33:05,845][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:33:06,355][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:33:06,865][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:33:07,375][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:33:07,887][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:33:08,398][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:33:08,907][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:33:09,417][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:33:09,928][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:33:10,438][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:33:10,946][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:33:11,455][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:33:11,965][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:33:12,473][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:33:12,981][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:33:13,491][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:33:14,000][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:33:14,511][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:33:15,021][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:33:15,531][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:33:16,041][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:33:16,552][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:33:17,063][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:33:17,573][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:33:18,083][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:33:18,593][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:33:19,103][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:33:19,613][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:33:20,123][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:33:20,633][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:33:21,143][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:33:21,653][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:33:22,162][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:33:22,673][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:33:23,183][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:33:23,694][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:33:24,205][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:33:24,715][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:33:25,227][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:33:25,738][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:33:26,249][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:33:26,758][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:33:27,267][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:33:27,776][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:33:28,284][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:33:28,793][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:33:29,302][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:33:29,811][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:33:30,319][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:33:30,830][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:33:31,339][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:33:31,848][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:33:32,357][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:33:32,865][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:33:33,374][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:33:33,882][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:33:34,392][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:33:34,900][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:33:35,410][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:33:35,919][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:33:36,430][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:33:36,940][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:33:37,449][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:33:37,959][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:33:38,469][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21731 tokens. [2026-03-25 23:33:39,140][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:05 [2026-03-25 23:33:39,898][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:33:39,901][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:33:39,902][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:33:40,714][__main__][INFO] - Iteration 365 took 1m 17s (10.61% Gen, 88.34% Train). Generation: 8s, Training: 1m 8s. Estimated remaining time: 56h 30m 50s. Estimated total time: 64h 29m 18s. Time estimates for 10 more iterations: 12m 53s, 100 more iterations: 2h 8m 58s, 500 more iterations: 10h 44m 53s. [2026-03-25 23:33:40,716][__main__][INFO] - Starting iteration 365. [2026-03-25 23:33:41,121][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:33:41,122][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:33:41,741][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:33:47,679][__main__][INFO] - Number of regex retries in iteration 365: 1 [2026-03-25 23:33:47,680][__main__][INFO] - agents played in iteration 365 are Bob, Alice [2026-03-25 23:33:48,629][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:33:49,270][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:33:49,732][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:33:50,246][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:33:50,754][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:33:51,263][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:33:51,771][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:33:52,279][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:33:52,788][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:33:53,296][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:33:53,803][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:33:54,310][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:33:54,817][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:33:55,326][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:33:55,833][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:33:56,340][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:33:56,848][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:33:57,356][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:33:57,866][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:33:58,374][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:33:58,882][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:33:59,390][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:33:59,898][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:34:00,406][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:34:00,914][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:34:01,421][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:34:01,933][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:34:02,442][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:34:02,951][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:34:03,460][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:34:03,969][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:34:04,477][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:34:04,985][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:34:05,494][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:34:06,002][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:34:06,511][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:34:07,019][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:34:07,530][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:34:08,039][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:34:08,548][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:34:09,056][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:34:09,566][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:34:10,078][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:34:10,589][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:34:11,098][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:34:11,607][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:34:12,117][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:34:12,627][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:34:13,137][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:34:13,646][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:34:14,155][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:34:14,663][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:34:15,172][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:34:15,680][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:34:16,189][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:34:16,698][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:34:17,206][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:34:17,715][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:34:18,222][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:34:18,732][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:34:19,240][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:34:19,748][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:34:20,256][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:34:20,765][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:34:21,273][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:34:21,782][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:34:22,290][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:34:22,799][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:34:23,307][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:34:23,816][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:34:24,327][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:34:24,835][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:34:25,344][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:34:25,855][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:34:26,363][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:34:26,871][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:34:27,379][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:34:27,886][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:34:28,394][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:34:28,901][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:34:29,410][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:34:29,918][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:34:30,428][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:34:30,937][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:34:31,446][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:34:31,955][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:34:32,465][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:34:32,974][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:34:33,481][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:34:33,990][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:34:34,499][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:34:35,008][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:34:35,517][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:34:36,026][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:34:36,534][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:34:37,044][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:34:37,553][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:34:38,062][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:34:38,570][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:34:39,078][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:34:39,589][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:34:40,098][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:34:40,607][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:34:41,115][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:34:41,625][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:34:42,134][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:34:42,643][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:34:43,152][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:34:43,660][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:34:44,169][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:34:44,677][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:34:45,189][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:34:45,698][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:34:46,207][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:34:46,715][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:34:47,224][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:34:47,732][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:34:48,240][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:34:48,747][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:34:49,255][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:34:49,763][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:34:50,271][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:34:50,779][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:34:51,288][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:34:51,796][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:34:52,305][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:34:52,814][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:34:53,322][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:34:53,830][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:34:54,339][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 23:34:55,011][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 23:34:55,759][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:34:55,761][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:34:55,762][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:34:56,557][__main__][INFO] - Iteration 366 took 1m 15s (8.69% Gen, 90.25% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 52m 6s. Estimated total time: 62h 51m 49s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 43s, 500 more iterations: 10h 28m 38s. [2026-03-25 23:34:56,559][__main__][INFO] - Starting iteration 366. [2026-03-25 23:34:56,962][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:34:56,963][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:35:02,082][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 1, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:35:03,836][__main__][INFO] - Number of regex retries in iteration 366: 1 [2026-03-25 23:35:03,837][__main__][INFO] - agents played in iteration 366 are Bob, Alice [2026-03-25 23:35:04,787][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:35:05,423][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:35:05,887][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:35:06,399][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:35:06,909][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:35:07,418][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:35:07,928][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:35:08,436][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:35:08,945][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:35:09,453][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:35:09,961][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:35:10,469][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:35:10,977][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:35:11,484][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:35:11,993][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:35:12,501][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:35:13,008][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:35:13,516][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:35:14,030][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:35:14,540][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:35:15,048][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:35:15,557][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:35:16,067][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:35:16,576][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:35:17,085][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:35:17,594][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:35:18,103][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:35:18,610][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:35:19,117][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:35:19,628][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:35:20,137][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:35:20,645][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:35:21,153][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:35:21,661][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:35:22,167][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:35:22,671][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:35:23,176][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:35:23,681][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:35:24,186][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:35:24,691][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:35:25,196][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:35:25,700][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:35:26,208][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:35:26,717][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:35:27,225][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:35:27,734][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:35:28,243][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:35:28,752][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:35:29,259][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:35:29,768][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:35:30,280][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:35:30,792][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:35:31,303][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:35:31,815][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:35:32,325][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:35:32,837][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:35:33,350][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:35:33,862][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:35:34,369][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:35:34,876][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:35:35,384][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:35:35,892][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:35:36,399][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:35:36,907][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:35:37,416][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:35:37,924][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:35:38,433][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:35:38,940][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:35:39,449][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:35:39,956][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:35:40,464][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:35:40,972][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:35:41,479][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:35:41,987][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:35:42,495][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:35:43,005][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:35:43,513][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:35:44,021][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:35:44,529][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:35:45,037][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:35:45,546][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:35:46,054][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:35:46,563][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:35:47,072][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:35:47,581][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:35:48,091][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:35:48,598][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:35:49,108][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:35:49,617][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:35:50,128][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:35:50,637][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:35:51,146][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:35:51,655][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:35:52,162][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:35:52,670][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:35:53,179][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:35:53,687][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:35:54,194][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:35:54,700][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:35:55,205][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:35:55,709][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:35:56,215][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:35:56,719][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:35:57,225][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:35:57,730][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:35:58,235][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:35:58,743][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:35:59,251][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:35:59,759][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:36:00,267][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:36:00,775][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:36:01,284][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:36:01,793][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:36:02,301][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:36:02,812][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:36:03,324][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:36:03,837][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:36:04,348][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:36:04,859][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:36:05,371][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:36:05,883][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:36:06,395][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:36:06,903][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:36:07,411][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:36:07,918][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:36:08,426][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:36:08,934][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:36:09,441][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:36:09,949][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:36:10,457][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 23:36:11,128][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.15%, Current % of VRAM taken: 60.51%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:05 [2026-03-25 23:36:11,876][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:36:11,878][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:36:11,880][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:36:12,541][__main__][INFO] - Iteration 367 took 1m 15s (9.09% Gen, 90.03% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 57m 59s. Estimated total time: 62h 58m 58s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 57s, 500 more iterations: 10h 29m 49s. [2026-03-25 23:36:12,544][__main__][INFO] - Starting iteration 367. [2026-03-25 23:36:12,947][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:36:12,948][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:36:13,553][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 0 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:36:16,689][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:36:18,142][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:36:20,365][__main__][INFO] - Number of regex retries in iteration 367: 3 [2026-03-25 23:36:20,366][__main__][INFO] - agents played in iteration 367 are Bob, Alice [2026-03-25 23:36:21,315][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:36:21,949][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:36:22,412][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:36:22,927][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:36:23,435][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:36:23,943][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:36:24,451][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:36:24,958][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:36:25,467][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:36:25,975][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:36:26,487][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:36:26,997][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:36:27,507][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:36:28,016][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:36:28,527][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:36:29,037][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:36:29,548][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:36:30,058][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:36:30,567][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:36:31,075][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:36:31,586][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:36:32,095][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:36:32,603][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:36:33,112][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:36:33,620][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:36:34,128][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:36:34,638][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:36:35,148][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:36:35,656][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:36:36,165][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:36:36,674][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:36:37,183][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:36:37,691][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:36:38,198][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:36:38,711][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:36:39,219][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:36:39,729][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:36:40,239][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:36:40,749][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:36:41,259][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:36:41,766][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:36:42,275][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:36:42,784][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:36:43,293][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:36:43,800][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:36:44,309][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:36:44,817][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:36:45,325][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:36:45,834][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:36:46,343][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:36:46,851][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:36:47,359][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:36:47,866][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:36:48,373][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:36:48,879][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:36:49,387][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:36:49,893][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:36:50,401][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:36:50,910][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:36:51,420][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:36:51,928][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:36:52,438][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:36:52,948][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:36:53,457][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:36:53,967][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:36:54,475][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:36:54,983][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:36:55,491][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:36:55,999][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:36:56,510][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:36:57,019][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:36:57,528][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:36:58,036][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:36:58,546][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:36:59,055][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:36:59,565][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:37:00,074][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:37:00,585][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:37:01,094][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:37:01,603][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:37:02,113][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:37:02,624][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:37:03,132][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:37:03,641][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:37:04,149][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:37:04,658][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:37:05,166][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:37:05,674][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:37:06,183][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:37:06,692][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:37:07,199][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:37:07,710][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:37:08,220][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:37:08,729][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:37:09,238][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:37:09,747][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:37:10,256][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:37:10,765][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:37:11,275][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:37:11,786][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:37:12,295][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:37:12,805][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:37:13,315][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:37:13,825][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:37:14,335][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:37:14,846][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:37:15,354][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:37:15,862][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:37:16,370][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:37:16,878][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:37:17,386][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:37:17,894][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:37:18,402][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:37:18,910][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:37:19,418][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:37:19,925][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:37:20,433][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:37:20,941][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:37:21,449][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:37:21,957][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:37:22,464][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:37:22,973][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:37:23,481][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:37:23,990][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:37:24,497][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:37:25,005][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:37:25,513][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:37:26,022][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:37:26,531][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:37:27,039][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21748 tokens. [2026-03-25 23:37:27,711][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 23:37:28,460][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:37:28,462][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:37:28,464][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:37:29,137][__main__][INFO] - Iteration 368 took 1m 16s (9.74% Gen, 89.38% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 27m 13s. Estimated total time: 63h 29m 29s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 58s, 500 more iterations: 10h 34m 54s. [2026-03-25 23:37:29,139][__main__][INFO] - Starting iteration 368. [2026-03-25 23:37:29,540][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:37:29,541][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:37:30,159][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:37:36,613][__main__][INFO] - Number of regex retries in iteration 368: 1 [2026-03-25 23:37:36,614][__main__][INFO] - agents played in iteration 368 are Bob, Alice [2026-03-25 23:37:37,577][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:37:38,215][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:37:38,679][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:37:39,193][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:37:39,702][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:37:40,212][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:37:40,720][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:37:41,229][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:37:41,737][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:37:42,246][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:37:42,754][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:37:43,263][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:37:43,771][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:37:44,280][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:37:44,788][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:37:45,297][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:37:45,806][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:37:46,315][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:37:46,824][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:37:47,333][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:37:47,842][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:37:48,351][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:37:48,860][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:37:49,369][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:37:49,877][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:37:50,386][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:37:50,895][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:37:51,404][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:37:51,912][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:37:52,420][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:37:52,930][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:37:53,439][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:37:53,948][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:37:54,457][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:37:54,969][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:37:55,478][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:37:55,987][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:37:56,496][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:37:57,006][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:37:57,515][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:37:58,023][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:37:58,532][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:37:59,039][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:37:59,545][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:38:00,051][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:38:00,558][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:38:01,064][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:38:01,570][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:38:02,076][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:38:02,582][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:38:03,090][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:38:03,598][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:38:04,106][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:38:04,613][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:38:05,121][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:38:05,629][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:38:06,136][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:38:06,645][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:38:07,153][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:38:07,661][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:38:08,169][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:38:08,677][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:38:09,185][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:38:09,693][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:38:10,201][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:38:10,710][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:38:11,220][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:38:11,728][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:38:12,236][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:38:12,745][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:38:13,253][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:38:13,761][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:38:14,269][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:38:14,776][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:38:15,284][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:38:15,792][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:38:16,300][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:38:16,808][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:38:17,317][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:38:17,825][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:38:18,334][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:38:18,841][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:38:19,350][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:38:19,859][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:38:20,368][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:38:20,877][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:38:21,385][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:38:21,893][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:38:22,402][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:38:22,911][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:38:23,419][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:38:23,927][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:38:24,436][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:38:24,945][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:38:25,453][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:38:25,961][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:38:26,469][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:38:26,978][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:38:27,486][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:38:27,994][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:38:28,504][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:38:29,013][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:38:29,523][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:38:30,031][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:38:30,540][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:38:31,049][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:38:31,556][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:38:32,063][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:38:32,570][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:38:33,076][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:38:33,582][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:38:34,090][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:38:34,596][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:38:35,102][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:38:35,611][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:38:36,121][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:38:36,630][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:38:37,140][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:38:37,648][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:38:38,156][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:38:38,665][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:38:39,174][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:38:39,682][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:38:40,190][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:38:40,699][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:38:41,210][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:38:41,714][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:38:42,224][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:38:42,733][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:38:43,242][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21727 tokens. [2026-03-25 23:38:43,902][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 23:38:44,651][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:38:44,654][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:38:44,655][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:38:45,311][__main__][INFO] - Iteration 369 took 1m 15s (9.33% Gen, 89.80% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 5m 3s. Estimated total time: 63h 8m 35s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 17s, 500 more iterations: 10h 31m 25s. [2026-03-25 23:38:45,313][__main__][INFO] - Starting iteration 369. [2026-03-25 23:38:45,717][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:38:45,717][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:38:52,641][__main__][INFO] - Number of regex retries in iteration 369: 0 [2026-03-25 23:38:52,643][__main__][INFO] - agents played in iteration 369 are Bob, Alice [2026-03-25 23:38:53,887][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:38:54,512][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:38:54,977][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:38:55,491][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:38:56,000][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:38:56,508][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:38:57,018][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:38:57,529][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:38:58,038][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:38:58,547][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:38:59,055][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:38:59,566][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:39:00,075][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:39:00,583][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:39:01,090][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:39:01,598][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:39:02,106][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:39:02,614][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:39:03,122][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:39:03,629][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:39:04,137][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:39:04,645][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:39:05,152][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:39:05,658][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:39:06,166][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:39:06,673][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:39:07,181][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:39:07,690][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:39:08,199][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:39:08,707][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:39:09,216][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:39:09,724][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:39:10,233][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:39:10,742][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:39:11,249][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:39:11,756][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:39:12,262][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:39:12,769][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:39:13,275][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:39:13,783][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:39:14,290][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:39:14,796][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:39:15,304][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:39:15,811][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:39:16,320][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:39:16,829][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:39:17,337][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:39:17,845][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:39:18,354][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:39:18,862][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:39:19,371][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:39:19,879][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:39:20,387][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:39:20,895][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:39:21,405][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:39:21,913][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:39:22,421][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:39:22,930][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:39:23,439][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:39:23,947][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:39:24,455][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:39:24,962][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:39:25,470][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:39:25,978][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:39:26,485][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:39:26,993][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:39:27,501][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:39:28,010][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:39:28,519][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:39:29,028][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:39:29,538][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:39:30,046][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:39:30,555][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:39:31,063][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:39:31,572][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:39:32,079][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:39:32,587][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:39:33,095][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:39:33,603][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:39:34,110][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:39:34,618][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:39:35,129][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:39:35,637][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:39:36,145][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:39:36,653][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:39:37,161][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:39:37,669][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:39:38,177][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:39:38,685][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:39:39,193][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:39:39,702][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:39:40,211][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:39:40,719][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:39:41,230][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:39:41,738][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:39:42,247][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:39:42,755][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:39:43,265][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:39:43,772][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:39:44,278][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:39:44,787][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:39:45,293][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:39:45,799][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:39:46,307][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:39:46,814][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:39:47,321][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:39:47,829][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:39:48,337][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:39:48,845][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:39:49,354][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:39:49,861][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:39:50,369][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:39:50,877][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:39:51,386][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:39:51,895][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:39:52,404][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:39:52,913][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:39:53,422][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:39:53,931][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:39:54,440][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:39:54,949][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:39:55,458][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:39:55,967][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:39:56,474][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:39:56,981][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:39:57,489][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:39:57,996][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:39:58,505][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:39:59,012][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:39:59,519][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21740 tokens. [2026-03-25 23:40:00,173][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-25 23:40:00,911][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:40:00,913][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:40:00,915][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:40:01,593][__main__][INFO] - Iteration 370 took 1m 15s (9.13% Gen, 89.98% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 9m 1s. Estimated total time: 63h 13m 49s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 27s, 500 more iterations: 10h 32m 18s. [2026-03-25 23:40:01,595][__main__][INFO] - Starting iteration 370. [2026-03-25 23:40:01,995][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:40:01,995][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:40:02,626][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:40:08,987][__main__][INFO] - Number of regex retries in iteration 370: 1 [2026-03-25 23:40:08,988][__main__][INFO] - agents played in iteration 370 are Bob, Alice [2026-03-25 23:40:09,944][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:40:10,569][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:40:11,035][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:40:11,549][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:40:12,058][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:40:12,566][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:40:13,074][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:40:13,583][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:40:14,092][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:40:14,599][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:40:15,108][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:40:15,616][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:40:16,126][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:40:16,636][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:40:17,145][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:40:17,654][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:40:18,162][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:40:18,671][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:40:19,180][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:40:19,688][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:40:20,197][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:40:20,707][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:40:21,215][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:40:21,733][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:40:22,242][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:40:22,750][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:40:23,259][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:40:23,766][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:40:24,274][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:40:24,782][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:40:25,290][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:40:25,797][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:40:26,305][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:40:26,814][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:40:27,320][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:40:27,829][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:40:28,337][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:40:28,845][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:40:29,353][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:40:29,860][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:40:30,368][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:40:30,876][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:40:31,385][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:40:31,892][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:40:32,399][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:40:32,907][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:40:33,415][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:40:33,924][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:40:34,432][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:40:34,939][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:40:35,450][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:40:35,960][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:40:36,469][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:40:36,979][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:40:37,489][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:40:37,998][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:40:38,508][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:40:39,017][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:40:39,528][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:40:40,038][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:40:40,546][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:40:41,056][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:40:41,565][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:40:42,074][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:40:42,582][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:40:43,091][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:40:43,600][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:40:44,108][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:40:44,617][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:40:45,126][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:40:45,635][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:40:46,143][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:40:46,651][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:40:47,160][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:40:47,669][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:40:48,177][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:40:48,685][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:40:49,194][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:40:49,703][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:40:50,213][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:40:50,722][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:40:51,231][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:40:51,739][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:40:52,247][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:40:52,756][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:40:53,266][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:40:53,775][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:40:54,283][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:40:54,792][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:40:55,300][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:40:55,808][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:40:56,316][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:40:56,825][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:40:57,333][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:40:57,840][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:40:58,344][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:40:58,852][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:40:59,361][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:40:59,868][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:41:00,376][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:41:00,884][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:41:01,391][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:41:01,898][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:41:02,407][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:41:02,914][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:41:03,422][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:41:03,931][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:41:04,439][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:41:04,948][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:41:05,457][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:41:05,964][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:41:06,471][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:41:06,978][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:41:07,486][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:41:07,994][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:41:08,502][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:41:09,011][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:41:09,520][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:41:10,030][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:41:10,539][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:41:11,048][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:41:11,558][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:41:12,066][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:41:12,575][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:41:13,083][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:41:13,591][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:41:14,099][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:41:14,609][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:41:15,118][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:41:15,628][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-25 23:41:16,289][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-25 23:41:17,030][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:41:17,033][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:41:17,034][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:41:17,688][__main__][INFO] - Iteration 371 took 1m 15s (9.24% Gen, 89.90% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 58m 36s. Estimated total time: 63h 4m 40s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 9s, 500 more iterations: 10h 30m 46s. [2026-03-25 23:41:17,690][__main__][INFO] - Starting iteration 371. [2026-03-25 23:41:18,093][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:41:18,093][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:41:25,285][__main__][INFO] - Number of regex retries in iteration 371: 0 [2026-03-25 23:41:25,286][__main__][INFO] - agents played in iteration 371 are Bob, Alice [2026-03-25 23:41:26,254][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:41:26,873][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:41:27,336][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:41:27,849][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:41:28,356][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:41:28,864][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:41:29,372][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:41:29,879][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:41:30,386][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:41:30,892][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:41:31,402][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:41:31,911][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:41:32,419][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:41:32,928][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:41:33,438][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:41:33,947][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:41:34,455][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:41:34,962][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:41:35,473][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:41:35,981][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:41:36,489][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:41:36,998][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:41:37,508][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:41:38,017][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:41:38,527][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:41:39,037][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:41:39,546][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:41:40,056][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:41:40,564][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:41:41,072][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:41:41,579][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:41:42,087][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:41:42,594][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:41:43,102][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:41:43,611][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:41:44,119][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:41:44,630][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:41:45,138][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:41:45,647][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:41:46,156][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:41:46,666][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:41:47,175][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:41:47,684][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:41:48,193][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:41:48,703][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:41:49,212][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:41:49,722][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:41:50,232][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:41:50,742][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:41:51,252][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:41:51,760][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:41:52,270][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:41:52,779][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:41:53,288][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:41:53,797][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:41:54,307][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:41:54,816][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:41:55,326][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:41:55,835][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:41:56,344][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:41:56,854][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:41:57,363][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:41:57,872][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:41:58,380][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:41:58,889][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:41:59,399][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:41:59,907][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:42:00,415][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:42:00,923][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:42:01,432][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:42:01,940][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:42:02,448][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:42:02,956][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:42:03,464][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:42:03,972][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:42:04,480][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:42:04,989][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:42:05,498][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:42:06,006][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:42:06,514][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:42:07,023][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:42:07,531][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:42:08,041][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:42:08,550][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:42:09,060][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:42:09,570][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:42:10,081][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:42:10,591][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:42:11,100][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:42:11,609][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:42:12,117][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:42:12,630][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:42:13,139][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:42:13,647][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:42:14,157][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:42:14,666][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:42:15,175][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:42:15,684][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:42:16,192][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:42:16,701][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:42:17,208][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:42:17,717][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:42:18,228][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:42:18,738][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:42:19,246][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:42:19,755][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:42:20,265][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:42:20,774][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:42:21,284][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:42:21,793][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:42:22,302][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:42:22,811][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:42:23,320][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:42:23,831][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:42:24,341][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:42:24,852][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:42:25,361][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:42:25,870][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:42:26,380][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:42:26,889][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:42:27,398][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:42:27,909][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:42:28,418][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:42:28,929][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:42:29,439][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:42:29,949][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:42:30,458][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:42:30,967][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:42:31,477][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:42:31,986][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-25 23:42:32,653][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 23:42:33,400][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:42:33,402][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:42:33,404][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:42:34,062][__main__][INFO] - Iteration 372 took 1m 15s (9.47% Gen, 89.66% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 11m 9s. Estimated total time: 63h 18m 30s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 37s, 500 more iterations: 10h 33m 5s. [2026-03-25 23:42:34,064][__main__][INFO] - Starting iteration 372. [2026-03-25 23:42:34,478][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:42:34,479][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:42:41,247][__main__][INFO] - Number of regex retries in iteration 372: 0 [2026-03-25 23:42:41,248][__main__][INFO] - agents played in iteration 372 are Bob, Alice [2026-03-25 23:42:42,205][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:42:42,833][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:42:43,299][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:42:43,813][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:42:44,322][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:42:44,831][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:42:45,340][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:42:45,848][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:42:46,358][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:42:46,868][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:42:47,381][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:42:47,891][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:42:48,400][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:42:48,910][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:42:49,420][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:42:49,931][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:42:50,441][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:42:50,952][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:42:51,459][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:42:51,968][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:42:52,476][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:42:52,983][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:42:53,490][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:42:53,997][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:42:54,506][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:42:55,013][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:42:55,523][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:42:56,032][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:42:56,541][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:42:57,050][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:42:57,558][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:42:58,068][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:42:58,576][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:42:59,085][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:42:59,594][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:43:00,104][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:43:00,613][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:43:01,123][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:43:01,633][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:43:02,142][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:43:02,651][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:43:03,160][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:43:03,668][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:43:04,176][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:43:04,685][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:43:05,192][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:43:05,700][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:43:06,208][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:43:06,716][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:43:07,225][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:43:07,733][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:43:08,242][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:43:08,752][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:43:09,261][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:43:09,769][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:43:10,279][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:43:10,790][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:43:11,299][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:43:11,809][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:43:12,318][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:43:12,831][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:43:13,342][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:43:13,851][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:43:14,359][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:43:14,869][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:43:15,379][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:43:15,887][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:43:16,396][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:43:16,906][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:43:17,415][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:43:17,924][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:43:18,433][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:43:18,943][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:43:19,452][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:43:19,960][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:43:20,470][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:43:20,979][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:43:21,490][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:43:21,999][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:43:22,509][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:43:23,019][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:43:23,530][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:43:24,039][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:43:24,547][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:43:25,055][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:43:25,562][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:43:26,070][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:43:26,578][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:43:27,085][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:43:27,593][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:43:28,103][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:43:28,611][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:43:29,119][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:43:29,630][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:43:30,140][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:43:30,648][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:43:31,158][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:43:31,668][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:43:32,177][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:43:32,687][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:43:33,197][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:43:33,707][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:43:34,217][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:43:34,727][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:43:35,237][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:43:35,746][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:43:36,255][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:43:36,763][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:43:37,272][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:43:37,780][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:43:38,290][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:43:38,799][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:43:39,309][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:43:39,819][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:43:40,329][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:43:40,839][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:43:41,349][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:43:41,859][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:43:42,369][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:43:42,879][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:43:43,390][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:43:43,898][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:43:44,408][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:43:44,918][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:43:45,429][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:43:45,940][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:43:46,451][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:43:46,961][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:43:47,472][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:43:47,982][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-25 23:43:48,642][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:05 [2026-03-25 23:43:49,397][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:43:49,399][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:43:49,401][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:43:50,071][__main__][INFO] - Iteration 373 took 1m 15s (8.95% Gen, 90.16% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 51m 3s. Estimated total time: 62h 59m 40s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 59s, 500 more iterations: 10h 29m 56s. [2026-03-25 23:43:50,073][__main__][INFO] - Starting iteration 373. [2026-03-25 23:43:50,477][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:43:50,478][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:43:54,204][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:43:57,666][__main__][INFO] - Number of regex retries in iteration 373: 1 [2026-03-25 23:43:57,667][__main__][INFO] - agents played in iteration 373 are Bob, Alice [2026-03-25 23:43:58,640][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:43:59,273][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:43:59,741][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:44:00,256][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:44:00,766][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:44:01,277][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:44:01,786][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:44:02,294][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:44:02,803][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:44:03,313][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:44:03,820][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:44:04,330][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:44:04,837][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:44:05,346][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:44:05,854][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:44:06,361][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:44:06,869][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:44:07,377][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:44:07,885][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:44:08,393][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:44:08,901][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:44:09,409][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:44:09,917][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:44:10,425][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:44:10,934][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:44:11,443][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:44:11,952][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:44:12,460][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:44:12,968][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:44:13,477][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:44:13,985][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:44:14,493][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:44:15,001][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:44:15,509][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:44:16,017][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:44:16,527][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:44:17,035][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:44:17,543][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:44:18,052][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:44:18,559][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:44:19,067][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:44:19,574][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:44:20,083][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:44:20,591][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:44:21,099][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:44:21,608][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:44:22,116][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:44:22,623][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:44:23,132][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:44:23,639][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:44:24,148][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:44:24,657][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:44:25,166][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:44:25,673][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:44:26,182][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:44:26,690][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:44:27,198][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:44:27,707][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:44:28,215][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:44:28,724][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:44:29,232][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:44:29,740][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:44:30,249][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:44:30,758][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:44:31,266][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:44:31,774][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:44:32,283][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:44:32,791][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:44:33,300][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:44:33,809][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:44:34,318][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:44:34,827][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:44:35,337][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:44:35,848][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:44:36,357][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:44:36,867][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:44:37,374][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:44:37,884][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:44:38,391][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:44:38,900][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:44:39,408][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:44:39,916][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:44:40,425][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:44:40,933][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:44:41,441][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:44:41,949][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:44:42,457][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:44:42,965][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:44:43,473][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:44:43,981][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:44:44,489][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:44:44,998][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:44:45,507][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:44:46,016][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:44:46,523][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:44:47,032][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:44:47,539][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:44:48,048][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:44:48,556][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:44:49,064][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:44:49,572][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:44:50,081][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:44:50,588][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:44:51,095][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:44:51,602][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:44:52,111][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:44:52,619][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:44:53,128][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:44:53,637][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:44:54,145][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:44:54,652][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:44:55,160][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:44:55,668][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:44:56,176][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:44:56,684][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:44:57,191][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:44:57,700][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:44:58,209][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:44:58,717][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:44:59,226][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:44:59,734][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:45:00,242][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:45:00,750][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:45:01,258][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:45:01,767][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:45:02,274][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:45:02,782][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:45:03,290][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:45:03,798][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:45:04,305][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21747 tokens. [2026-03-25 23:45:04,960][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-25 23:45:05,700][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:45:05,703][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:45:05,705][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:45:06,362][__main__][INFO] - Iteration 374 took 1m 15s (9.47% Gen, 89.66% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 4m 23s. Estimated total time: 63h 14m 16s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 28s, 500 more iterations: 10h 32m 22s. [2026-03-25 23:45:06,364][__main__][INFO] - Starting iteration 374. [2026-03-25 23:45:06,764][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:45:06,764][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:45:07,391][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:45:12,856][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:45:13,643][__main__][INFO] - Number of regex retries in iteration 374: 2 [2026-03-25 23:45:13,644][__main__][INFO] - agents played in iteration 374 are Bob, Alice [2026-03-25 23:45:14,897][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:45:15,529][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:45:15,995][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:45:16,509][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:45:17,018][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:45:17,529][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:45:18,037][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:45:18,547][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:45:19,056][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:45:19,565][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:45:20,077][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:45:20,586][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:45:21,095][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:45:21,604][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:45:22,114][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:45:22,624][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:45:23,134][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:45:23,643][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:45:24,152][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:45:24,661][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:45:25,169][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:45:25,677][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:45:26,187][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:45:26,697][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:45:27,206][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:45:27,715][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:45:28,223][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:45:28,731][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:45:29,239][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:45:29,748][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:45:30,256][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:45:30,764][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:45:31,272][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:45:31,779][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:45:32,288][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:45:32,795][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:45:33,301][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:45:33,809][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:45:34,316][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:45:34,823][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:45:35,332][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:45:35,840][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:45:36,349][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:45:36,858][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:45:37,366][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:45:37,874][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:45:38,382][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:45:38,891][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:45:39,398][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:45:39,906][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:45:40,414][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:45:40,922][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:45:41,430][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:45:41,938][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:45:42,446][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:45:42,955][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:45:43,463][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:45:43,971][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:45:44,478][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:45:44,986][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:45:45,493][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:45:45,999][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:45:46,507][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:45:47,015][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:45:47,523][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:45:48,031][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:45:48,539][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:45:49,047][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:45:49,556][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:45:50,064][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:45:50,572][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:45:51,080][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:45:51,590][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:45:52,098][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:45:52,607][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:45:53,115][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:45:53,623][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:45:54,132][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:45:54,639][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:45:55,145][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:45:55,653][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:45:56,161][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:45:56,669][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:45:57,178][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:45:57,688][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:45:58,195][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:45:58,703][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:45:59,210][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:45:59,717][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:46:00,227][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:46:00,735][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:46:01,242][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:46:01,749][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:46:02,258][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:46:02,765][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:46:03,273][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:46:03,780][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:46:04,287][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:46:04,794][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:46:05,300][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:46:05,809][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:46:06,317][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:46:06,825][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:46:07,332][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:46:07,840][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:46:08,348][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:46:08,858][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:46:09,365][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:46:09,873][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:46:10,381][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:46:10,889][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:46:11,397][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:46:11,906][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:46:12,414][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:46:12,921][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:46:13,429][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:46:13,938][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:46:14,446][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:46:14,955][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:46:15,465][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:46:15,973][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:46:16,482][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:46:16,990][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:46:17,498][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:46:18,006][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:46:18,514][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:46:19,021][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:46:19,529][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:46:20,038][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:46:20,546][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21716 tokens. [2026-03-25 23:46:21,209][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 23:46:21,954][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:46:21,957][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:46:21,958][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:46:22,668][__main__][INFO] - Iteration 375 took 1m 15s (9.06% Gen, 90.00% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 55h 4m 5s. Estimated total time: 63h 15m 14s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 30s, 500 more iterations: 10h 32m 32s. [2026-03-25 23:46:22,670][__main__][INFO] - Starting iteration 375. [2026-03-25 23:46:23,073][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:46:23,074][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:46:28,202][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:46:30,614][__main__][INFO] - Number of regex retries in iteration 375: 1 [2026-03-25 23:46:30,615][__main__][INFO] - agents played in iteration 375 are Bob, Alice [2026-03-25 23:46:31,578][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:46:32,212][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:46:32,679][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:46:33,193][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:46:33,703][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:46:34,213][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:46:34,723][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:46:35,234][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:46:35,743][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:46:36,253][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:46:36,762][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:46:37,269][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:46:37,777][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:46:38,285][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:46:38,793][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:46:39,300][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:46:39,809][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:46:40,316][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:46:40,827][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:46:41,339][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:46:41,849][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:46:42,359][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:46:42,869][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:46:43,378][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:46:43,888][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:46:44,397][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:46:44,908][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:46:45,417][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:46:45,926][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:46:46,435][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:46:46,943][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:46:47,453][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:46:47,962][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:46:48,471][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:46:48,979][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:46:49,488][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:46:49,997][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:46:50,506][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:46:51,015][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:46:51,524][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:46:52,032][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:46:52,541][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:46:53,050][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:46:53,558][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:46:54,065][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:46:54,573][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:46:55,081][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:46:55,589][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:46:56,098][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:46:56,606][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:46:57,114][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:46:57,623][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:46:58,132][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:46:58,640][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:46:59,148][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:46:59,657][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:47:00,165][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:47:00,673][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:47:01,182][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:47:01,690][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:47:02,197][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:47:02,709][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:47:03,218][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:47:03,727][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:47:04,235][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:47:04,744][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:47:05,253][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:47:05,762][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:47:06,272][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:47:06,780][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:47:07,289][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:47:07,798][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:47:08,310][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:47:08,821][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:47:09,329][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:47:09,837][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:47:10,345][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:47:10,854][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:47:11,362][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:47:11,869][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:47:12,376][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:47:12,884][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:47:13,393][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:47:13,901][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:47:14,411][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:47:14,920][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:47:15,430][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:47:15,940][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:47:16,449][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:47:16,959][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:47:17,468][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:47:17,977][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:47:18,486][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:47:18,994][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:47:19,504][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:47:20,013][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:47:20,521][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:47:21,031][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:47:21,540][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:47:22,050][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:47:22,559][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:47:23,067][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:47:23,576][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:47:24,086][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:47:24,594][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:47:25,103][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:47:25,610][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:47:26,117][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:47:26,626][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:47:27,134][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:47:27,642][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:47:28,150][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:47:28,657][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:47:29,165][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:47:29,674][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:47:30,183][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:47:30,692][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:47:31,200][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:47:31,709][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:47:32,218][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:47:32,729][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:47:33,238][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:47:33,746][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:47:34,254][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:47:34,763][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:47:35,271][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:47:35,779][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:47:36,286][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:47:36,795][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:47:37,303][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21741 tokens. [2026-03-25 23:47:37,965][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:05 [2026-03-25 23:47:38,703][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:47:38,706][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:47:38,707][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:47:39,359][__main__][INFO] - Iteration 376 took 1m 16s (9.88% Gen, 89.26% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 21m 52s. Estimated total time: 63h 34m 18s. Time estimates for 10 more iterations: 12m 42s, 100 more iterations: 2h 7m 8s, 500 more iterations: 10h 35m 43s. [2026-03-25 23:47:39,361][__main__][INFO] - Starting iteration 376. [2026-03-25 23:47:39,764][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:47:39,765][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:47:47,261][__main__][INFO] - Number of regex retries in iteration 376: 0 [2026-03-25 23:47:47,262][__main__][INFO] - agents played in iteration 376 are Bob, Alice [2026-03-25 23:47:48,226][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:47:48,854][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:47:49,321][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:47:49,836][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:47:50,344][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:47:50,854][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:47:51,363][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:47:51,872][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:47:52,381][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:47:52,890][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:47:53,398][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:47:53,906][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:47:54,415][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:47:54,923][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:47:55,431][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:47:55,939][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:47:56,448][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:47:56,957][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:47:57,465][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:47:57,973][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:47:58,480][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:47:58,990][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:47:59,499][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:48:00,006][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:48:00,514][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:48:01,022][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:48:01,529][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:48:02,038][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:48:02,546][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:48:03,054][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:48:03,562][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:48:04,069][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:48:04,577][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:48:05,087][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:48:05,596][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:48:06,105][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:48:06,614][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:48:07,125][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:48:07,633][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:48:08,141][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:48:08,651][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:48:09,161][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:48:09,668][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:48:10,176][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:48:10,683][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:48:11,191][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:48:11,698][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:48:12,207][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:48:12,715][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:48:13,222][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:48:13,732][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:48:14,241][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:48:14,750][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:48:15,261][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:48:15,770][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:48:16,279][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:48:16,789][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:48:17,298][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:48:17,807][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:48:18,315][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:48:18,823][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:48:19,333][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:48:19,842][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:48:20,350][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:48:20,859][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:48:21,367][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:48:21,877][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:48:22,386][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:48:22,895][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:48:23,405][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:48:23,915][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:48:24,424][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:48:24,933][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:48:25,443][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:48:25,951][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:48:26,460][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:48:26,969][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:48:27,477][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:48:27,986][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:48:28,495][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:48:29,002][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:48:29,513][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:48:30,021][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:48:30,531][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:48:31,040][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:48:31,549][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:48:32,058][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:48:32,566][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:48:33,075][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:48:33,583][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:48:34,091][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:48:34,598][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:48:35,108][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:48:35,617][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:48:36,126][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:48:36,634][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:48:37,143][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:48:37,651][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:48:38,160][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:48:38,669][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:48:39,178][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:48:39,687][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:48:40,195][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:48:40,704][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:48:41,213][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:48:41,722][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:48:42,232][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:48:42,740][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:48:43,248][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:48:43,758][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:48:44,265][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:48:44,773][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:48:45,281][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:48:45,791][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:48:46,299][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:48:46,808][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:48:47,317][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:48:47,827][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:48:48,336][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:48:48,846][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:48:49,356][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:48:49,864][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:48:50,373][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:48:50,881][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:48:51,389][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:48:51,896][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:48:52,404][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:48:52,912][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:48:53,420][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:48:53,929][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21750 tokens. [2026-03-25 23:48:54,601][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-25 23:48:55,341][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:48:55,343][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:48:55,345][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:48:56,004][__main__][INFO] - Iteration 377 took 1m 16s (9.83% Gen, 89.30% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 18m 20s. Estimated total time: 63h 32m 3s. Time estimates for 10 more iterations: 12m 42s, 100 more iterations: 2h 7m 4s, 500 more iterations: 10h 35m 20s. [2026-03-25 23:48:56,006][__main__][INFO] - Starting iteration 377. [2026-03-25 23:48:56,406][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:48:56,407][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:49:00,044][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:49:03,510][__main__][INFO] - Number of regex retries in iteration 377: 1 [2026-03-25 23:49:03,511][__main__][INFO] - agents played in iteration 377 are Bob, Alice [2026-03-25 23:49:04,469][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:49:05,100][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:49:05,565][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:49:06,078][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:49:06,586][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:49:07,095][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:49:07,604][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:49:08,112][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:49:08,619][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:49:09,130][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:49:09,642][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:49:10,151][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:49:10,659][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:49:11,170][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:49:11,678][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:49:12,186][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:49:12,695][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:49:13,204][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:49:13,712][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:49:14,219][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:49:14,730][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:49:15,239][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:49:15,748][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:49:16,257][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:49:16,765][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:49:17,273][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:49:17,784][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:49:18,294][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:49:18,803][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:49:19,312][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:49:19,821][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:49:20,333][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:49:20,843][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:49:21,352][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:49:21,862][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:49:22,371][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:49:22,880][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:49:23,390][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:49:23,898][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:49:24,407][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:49:24,916][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:49:25,427][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:49:25,937][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:49:26,447][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:49:26,957][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:49:27,468][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:49:27,978][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:49:28,488][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:49:28,997][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:49:29,508][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:49:30,017][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:49:30,528][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:49:31,038][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:49:31,549][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:49:32,058][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:49:32,568][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:49:33,077][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:49:33,586][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:49:34,093][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:49:34,599][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:49:35,106][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:49:35,613][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:49:36,121][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:49:36,628][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:49:37,135][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:49:37,643][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:49:38,152][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:49:38,660][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:49:39,169][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:49:39,678][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:49:40,186][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:49:40,693][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:49:41,202][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:49:41,710][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:49:42,219][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:49:42,729][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:49:43,239][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:49:43,748][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:49:44,257][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:49:44,767][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:49:45,276][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:49:45,786][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:49:46,293][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:49:46,800][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:49:47,308][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:49:47,816][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:49:48,325][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:49:48,834][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:49:49,342][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:49:49,850][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:49:50,360][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:49:50,870][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:49:51,380][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:49:51,889][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:49:52,398][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:49:52,907][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:49:53,416][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:49:53,928][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:49:54,438][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:49:54,946][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:49:55,455][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:49:55,965][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:49:56,474][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:49:56,984][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:49:57,492][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:49:58,001][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:49:58,509][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:49:59,018][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:49:59,530][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:50:00,041][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:50:00,550][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:50:01,059][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:50:01,569][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:50:02,079][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:50:02,587][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:50:03,097][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:50:03,607][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:50:04,117][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:50:04,629][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:50:05,140][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:50:05,649][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:50:06,159][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:50:06,665][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:50:07,171][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:50:07,678][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:50:08,184][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:50:08,692][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:50:09,199][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:50:09,705][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:50:10,213][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-25 23:50:10,886][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.14%, Current % of VRAM taken: 60.50%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 23:50:11,629][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:50:11,631][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:50:11,633][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:50:12,468][__main__][INFO] - Iteration 378 took 1m 16s (9.34% Gen, 89.56% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 8m 6s. Estimated total time: 63h 23m 5s. Time estimates for 10 more iterations: 12m 40s, 100 more iterations: 2h 6m 46s, 500 more iterations: 10h 33m 50s. [2026-03-25 23:50:12,470][__main__][INFO] - Starting iteration 378. [2026-03-25 23:50:12,872][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:50:12,873][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:50:20,099][__main__][INFO] - Number of regex retries in iteration 378: 0 [2026-03-25 23:50:20,100][__main__][INFO] - agents played in iteration 378 are Bob, Alice [2026-03-25 23:50:21,058][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:50:21,984][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:50:22,448][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:50:22,960][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:50:23,468][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:50:23,975][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:50:24,481][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:50:24,988][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:50:25,495][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:50:26,002][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:50:26,511][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:50:27,019][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:50:27,530][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:50:28,038][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:50:28,547][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:50:29,056][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:50:29,564][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:50:30,072][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:50:30,581][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:50:31,089][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:50:31,597][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:50:32,105][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:50:32,614][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:50:33,123][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:50:33,632][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:50:34,140][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:50:34,651][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:50:35,160][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:50:35,670][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:50:36,180][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:50:36,690][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:50:37,200][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:50:37,709][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:50:38,217][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:50:38,722][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:50:39,231][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:50:39,740][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:50:40,249][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:50:40,757][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:50:41,267][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:50:41,774][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:50:42,281][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:50:42,789][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:50:43,294][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:50:43,801][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:50:44,308][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:50:44,814][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:50:45,320][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:50:45,828][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:50:46,334][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:50:46,844][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:50:47,355][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:50:47,864][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:50:48,374][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:50:48,884][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:50:49,394][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:50:49,903][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:50:50,412][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:50:50,921][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:50:51,430][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:50:51,939][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:50:52,450][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:50:52,959][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:50:53,467][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:50:53,976][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:50:54,487][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:50:54,995][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:50:55,501][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:50:56,009][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:50:56,517][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:50:57,025][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:50:57,532][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:50:58,041][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:50:58,549][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:50:59,058][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:50:59,567][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:51:00,075][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:51:00,583][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:51:01,091][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:51:01,600][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:51:02,108][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:51:02,619][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:51:03,127][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:51:03,636][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:51:04,147][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:51:04,654][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:51:05,163][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:51:05,672][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:51:06,179][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:51:06,689][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:51:07,198][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:51:07,710][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:51:08,221][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:51:08,731][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:51:09,241][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:51:09,752][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:51:10,262][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:51:10,772][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:51:11,280][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:51:11,788][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:51:12,296][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:51:12,805][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:51:13,314][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:51:13,823][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:51:14,332][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:51:14,840][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:51:15,347][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:51:15,853][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:51:16,359][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:51:16,866][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:51:17,373][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:51:17,883][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:51:18,391][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:51:18,898][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:51:19,411][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:51:19,922][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:51:20,433][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:51:20,945][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:51:21,457][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:51:21,968][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:51:22,485][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:51:22,997][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:51:23,510][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:51:24,022][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:51:24,534][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:51:25,045][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:51:25,556][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:51:26,068][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:51:26,578][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:51:27,093][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-25 23:51:27,777][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.38%, ΔTime: 00:01:05 [2026-03-25 23:51:28,525][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:51:28,528][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:51:28,529][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:51:29,266][__main__][INFO] - Iteration 379 took 1m 16s (9.46% Gen, 89.57% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 23m 28s. Estimated total time: 63h 39m 44s. Time estimates for 10 more iterations: 12m 43s, 100 more iterations: 2h 7m 19s, 500 more iterations: 10h 36m 37s. [2026-03-25 23:51:29,268][__main__][INFO] - Starting iteration 379. [2026-03-25 23:51:29,683][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:51:29,683][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:51:37,042][__main__][INFO] - Number of regex retries in iteration 379: 0 [2026-03-25 23:51:37,043][__main__][INFO] - agents played in iteration 379 are Bob, Alice [2026-03-25 23:51:38,021][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:51:38,664][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:51:39,131][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:51:39,647][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:51:40,157][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:51:40,665][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:51:41,174][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:51:41,684][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:51:42,193][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:51:42,701][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:51:43,211][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:51:43,719][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:51:44,230][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:51:44,739][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:51:45,249][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:51:45,758][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:51:46,266][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:51:46,775][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:51:47,283][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:51:47,791][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:51:48,298][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:51:48,807][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:51:49,315][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:51:49,822][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:51:50,331][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:51:50,840][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:51:51,350][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:51:51,860][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:51:52,370][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:51:52,879][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:51:53,389][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:51:53,897][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:51:54,407][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:51:54,917][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:51:55,426][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:51:55,934][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:51:56,443][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:51:56,952][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:51:57,460][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:51:57,970][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:51:58,479][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:51:58,988][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:51:59,495][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:52:00,004][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:52:00,512][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:52:01,021][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:52:01,530][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:52:02,040][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:52:02,549][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:52:03,057][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:52:03,570][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:52:04,082][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:52:04,594][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:52:05,106][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:52:05,619][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:52:06,131][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:52:06,655][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:52:07,167][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:52:07,675][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:52:08,184][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:52:08,692][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:52:09,200][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:52:09,710][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:52:10,219][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:52:10,728][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:52:11,237][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:52:11,747][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:52:12,256][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:52:12,766][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:52:13,275][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:52:13,785][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:52:14,294][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:52:14,802][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:52:15,312][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:52:15,821][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:52:16,331][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:52:16,840][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:52:17,349][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:52:17,857][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:52:18,366][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:52:18,874][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:52:19,383][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:52:19,890][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:52:20,399][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:52:20,908][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:52:21,417][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:52:21,927][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:52:22,436][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:52:22,946][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:52:23,454][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:52:23,964][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:52:24,474][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:52:24,983][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:52:25,492][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:52:26,002][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:52:26,512][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:52:27,021][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:52:27,531][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:52:28,040][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:52:28,549][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:52:29,059][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:52:29,567][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:52:30,075][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:52:30,583][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:52:31,091][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:52:31,600][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:52:32,110][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:52:32,619][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:52:33,128][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:52:33,638][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:52:34,147][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:52:34,655][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:52:35,164][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:52:35,672][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:52:36,183][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:52:36,695][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:52:37,207][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:52:37,719][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:52:38,231][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:52:38,743][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:52:39,254][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:52:39,765][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:52:40,274][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:52:40,782][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:52:41,291][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:52:41,800][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:52:42,308][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:52:42,817][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:52:43,333][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:52:43,844][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 23:52:44,522][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:05 [2026-03-25 23:52:45,266][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:52:45,268][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:52:45,270][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:52:45,947][__main__][INFO] - Iteration 380 took 1m 16s (9.65% Gen, 89.46% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 15m 42s. Estimated total time: 63h 33m 15s. Time estimates for 10 more iterations: 12m 42s, 100 more iterations: 2h 7m 6s, 500 more iterations: 10h 35m 32s. [2026-03-25 23:52:45,951][__main__][INFO] - Starting iteration 380. [2026-03-25 23:52:46,355][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:52:46,356][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:52:47,558][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:52:52,427][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-25 23:52:53,523][__main__][INFO] - Number of regex retries in iteration 380: 2 [2026-03-25 23:52:53,524][__main__][INFO] - agents played in iteration 380 are Bob, Alice [2026-03-25 23:52:54,501][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:52:55,145][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:52:55,611][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:52:56,124][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:52:56,633][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:52:57,143][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:52:57,651][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:52:58,160][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:52:58,671][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:52:59,180][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:52:59,693][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:53:00,204][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:53:00,715][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:53:01,227][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:53:01,738][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:53:02,249][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:53:02,759][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:53:03,271][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:53:03,780][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:53:04,289][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:53:04,798][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:53:05,311][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:53:05,821][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:53:06,331][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:53:06,840][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:53:07,350][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:53:07,860][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:53:08,369][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:53:08,878][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:53:09,387][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:53:09,896][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:53:10,406][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:53:10,915][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:53:11,424][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:53:11,936][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:53:12,447][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:53:12,957][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:53:13,467][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:53:13,977][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:53:14,488][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:53:14,997][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:53:15,507][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:53:16,037][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:53:16,551][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:53:17,063][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:53:17,574][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:53:18,084][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:53:18,595][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:53:19,107][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:53:19,619][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:53:20,130][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:53:20,641][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:53:21,152][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:53:21,662][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:53:22,172][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:53:22,682][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:53:23,192][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:53:23,702][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:53:24,214][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:53:24,725][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:53:25,236][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:53:25,748][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:53:26,259][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:53:26,769][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:53:27,280][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:53:27,791][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:53:28,300][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:53:28,810][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:53:29,318][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:53:29,827][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:53:30,336][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:53:30,846][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:53:31,354][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:53:31,863][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:53:32,372][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:53:32,882][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:53:33,392][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:53:33,902][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:53:34,413][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:53:34,923][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:53:35,434][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:53:35,944][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:53:36,453][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:53:36,962][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:53:37,471][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:53:37,980][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:53:38,491][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:53:39,001][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:53:39,511][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:53:40,019][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:53:40,530][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:53:41,038][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:53:41,546][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:53:42,054][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:53:42,563][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:53:43,070][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:53:43,578][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:53:44,087][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:53:44,597][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:53:45,106][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:53:45,615][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:53:46,128][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:53:46,638][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:53:47,147][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:53:47,657][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:53:48,168][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:53:48,678][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:53:49,188][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:53:49,697][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:53:50,208][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:53:50,717][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:53:51,229][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:53:51,741][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:53:52,250][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:53:52,760][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:53:53,269][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:53:53,778][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:53:54,288][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:53:54,796][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:53:55,305][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:53:55,817][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:53:56,329][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:53:56,841][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:53:57,351][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:53:57,863][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:53:58,375][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:53:58,885][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:53:59,395][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:53:59,908][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:54:00,424][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21750 tokens. [2026-03-25 23:54:01,099][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-25 23:54:01,847][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:54:01,849][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:54:01,851][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:54:02,592][__main__][INFO] - Iteration 381 took 1m 16s (9.40% Gen, 89.62% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 13m 2s. Estimated total time: 63h 31m 52s. Time estimates for 10 more iterations: 12m 42s, 100 more iterations: 2h 7m 3s, 500 more iterations: 10h 35m 18s. [2026-03-25 23:54:02,595][__main__][INFO] - Starting iteration 381. [2026-03-25 23:54:02,997][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:54:02,997][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:54:10,136][__main__][INFO] - Number of regex retries in iteration 381: 0 [2026-03-25 23:54:10,136][__main__][INFO] - agents played in iteration 381 are Bob, Alice [2026-03-25 23:54:11,100][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:54:11,741][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:54:12,207][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:54:12,721][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:54:13,231][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:54:13,740][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:54:14,250][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:54:14,758][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:54:15,268][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:54:15,777][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:54:16,286][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:54:16,794][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:54:17,301][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:54:17,810][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:54:18,318][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:54:18,826][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:54:19,335][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:54:19,843][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:54:20,353][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:54:20,861][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:54:21,370][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:54:21,879][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:54:22,388][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:54:22,897][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:54:23,405][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:54:23,914][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:54:24,425][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:54:24,934][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:54:25,443][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:54:25,952][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:54:26,461][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:54:26,970][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:54:27,478][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:54:27,988][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:54:28,497][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:54:29,006][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:54:29,514][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:54:30,023][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:54:30,531][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:54:31,040][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:54:31,550][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:54:32,060][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:54:32,569][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:54:33,078][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:54:33,589][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:54:34,098][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:54:34,606][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:54:35,115][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:54:35,624][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:54:36,133][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:54:36,640][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:54:37,150][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:54:37,660][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:54:38,168][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:54:38,676][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:54:39,184][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:54:39,692][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:54:40,200][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:54:40,705][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:54:41,214][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:54:41,721][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:54:42,227][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:54:42,735][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:54:43,243][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:54:43,751][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:54:44,258][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:54:44,769][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:54:45,279][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:54:45,788][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:54:46,297][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:54:46,808][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:54:47,318][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:54:47,826][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:54:48,336][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:54:48,843][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:54:49,351][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:54:49,859][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:54:50,365][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:54:50,873][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:54:51,380][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:54:51,888][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:54:52,394][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:54:52,903][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:54:53,412][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:54:53,920][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:54:54,430][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:54:54,938][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:54:55,448][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:54:55,957][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:54:56,465][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:54:56,974][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:54:57,483][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:54:57,991][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:54:58,501][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:54:59,010][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:54:59,519][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:55:00,031][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:55:00,541][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:55:01,050][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:55:01,559][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:55:02,068][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:55:02,577][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:55:03,086][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:55:03,594][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:55:04,103][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:55:04,612][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:55:05,120][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:55:05,628][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:55:06,139][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:55:06,647][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:55:07,157][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:55:07,664][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:55:08,173][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:55:08,681][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:55:09,188][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:55:09,694][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:55:10,203][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:55:10,711][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:55:11,219][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:55:11,731][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:55:12,240][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:55:12,749][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:55:13,256][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:55:13,762][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:55:14,269][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:55:14,776][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:55:15,283][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:55:15,791][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:55:16,298][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:55:16,805][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-25 23:55:17,472][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-25 23:55:18,220][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:55:18,222][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:55:18,223][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:55:18,965][__main__][INFO] - Iteration 382 took 1m 15s (9.40% Gen, 89.62% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 58m 20s. Estimated total time: 63h 18m 25s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 36s, 500 more iterations: 10h 33m 4s. [2026-03-25 23:55:18,967][__main__][INFO] - Starting iteration 382. [2026-03-25 23:55:19,367][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:55:19,368][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:55:25,834][__main__][INFO] - Number of regex retries in iteration 382: 0 [2026-03-25 23:55:25,836][__main__][INFO] - agents played in iteration 382 are Bob, Alice [2026-03-25 23:55:27,082][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:55:27,708][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:55:28,176][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:55:28,692][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:55:29,203][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:55:29,714][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:55:30,225][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:55:30,736][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:55:31,247][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:55:31,766][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:55:32,277][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:55:32,787][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:55:33,297][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:55:33,807][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:55:34,318][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:55:34,829][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:55:35,340][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:55:35,850][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:55:36,372][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:55:36,883][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:55:37,394][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:55:37,906][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:55:38,417][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:55:38,928][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:55:39,439][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:55:39,951][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:55:40,460][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:55:40,970][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:55:41,480][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:55:41,990][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:55:42,500][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:55:43,010][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:55:43,519][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:55:44,028][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:55:44,538][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:55:45,050][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:55:45,560][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:55:46,070][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:55:46,579][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:55:47,089][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:55:47,598][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:55:48,109][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:55:48,618][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:55:49,128][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:55:49,638][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:55:50,147][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:55:50,657][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:55:51,166][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:55:51,674][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:55:52,183][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:55:52,692][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:55:53,200][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:55:53,711][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:55:54,221][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:55:54,731][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:55:55,241][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:55:55,750][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:55:56,259][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:55:56,768][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:55:57,277][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:55:57,788][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:55:58,298][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:55:58,807][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:55:59,316][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:55:59,827][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:56:00,337][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:56:00,848][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:56:01,358][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:56:01,868][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:56:02,379][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:56:02,890][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:56:03,399][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:56:03,909][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:56:04,419][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:56:04,929][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:56:05,438][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:56:05,947][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:56:06,455][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:56:06,963][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:56:07,471][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:56:07,979][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:56:08,488][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:56:08,997][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:56:09,507][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:56:10,016][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:56:10,526][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:56:11,035][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:56:11,544][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:56:12,053][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:56:12,563][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:56:13,070][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:56:13,578][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:56:14,085][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:56:14,593][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:56:15,100][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:56:15,608][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:56:16,115][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:56:16,626][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:56:17,136][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:56:17,645][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:56:18,155][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:56:18,663][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:56:19,172][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:56:19,680][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:56:20,191][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:56:20,699][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:56:21,207][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:56:21,715][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:56:22,223][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:56:22,732][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:56:23,240][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:56:23,749][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:56:24,257][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:56:24,766][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:56:25,274][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:56:25,782][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:56:26,291][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:56:26,799][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:56:27,309][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:56:27,817][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:56:28,327][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:56:28,836][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:56:29,346][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:56:29,855][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:56:30,364][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:56:30,873][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:56:31,382][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:56:31,892][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:56:32,401][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:56:32,911][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-25 23:56:33,569][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-25 23:56:34,322][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:56:34,324][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:56:34,326][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:56:35,066][__main__][INFO] - Iteration 383 took 1m 15s (8.54% Gen, 90.48% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 43m 37s. Estimated total time: 63h 4m 59s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 9s, 500 more iterations: 10h 30m 49s. [2026-03-25 23:56:35,069][__main__][INFO] - Starting iteration 383. [2026-03-25 23:56:35,468][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:56:35,469][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:56:43,132][__main__][INFO] - Number of regex retries in iteration 383: 0 [2026-03-25 23:56:43,133][__main__][INFO] - agents played in iteration 383 are Bob, Alice [2026-03-25 23:56:44,093][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:56:44,718][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:56:45,184][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:56:45,698][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:56:46,208][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:56:46,716][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:56:47,225][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:56:47,734][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:56:48,241][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:56:48,750][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:56:49,262][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:56:49,771][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:56:50,280][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:56:50,790][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:56:51,301][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:56:51,813][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:56:52,324][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:56:52,834][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:56:53,344][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:56:53,851][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:56:54,359][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:56:54,867][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:56:55,375][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:56:55,882][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:56:56,390][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:56:56,899][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:56:57,408][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:56:57,916][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:56:58,426][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:56:58,936][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:56:59,445][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:56:59,953][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:57:00,462][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:57:00,971][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:57:01,478][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:57:01,987][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:57:02,494][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:57:03,003][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:57:03,511][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:57:04,019][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:57:04,527][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:57:05,035][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:57:05,544][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:57:06,053][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:57:06,562][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:57:07,071][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:57:07,580][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:57:08,089][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:57:08,597][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:57:09,106][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:57:09,616][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:57:10,125][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:57:10,634][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:57:11,144][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:57:11,652][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:57:12,160][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:57:12,669][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:57:13,178][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:57:13,688][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:57:14,196][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:57:14,703][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:57:15,212][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:57:15,721][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:57:16,229][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:57:16,737][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:57:17,248][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:57:17,757][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:57:18,267][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:57:18,775][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:57:19,285][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:57:19,793][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:57:20,301][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:57:20,811][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:57:21,320][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:57:21,829][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:57:22,339][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:57:22,849][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:57:23,359][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:57:23,869][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:57:24,378][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:57:24,887][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:57:25,397][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:57:25,905][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:57:26,412][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:57:26,922][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:57:27,431][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:57:27,939][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:57:28,448][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:57:28,957][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:57:29,466][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:57:29,974][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:57:30,483][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:57:30,991][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:57:31,500][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:57:32,009][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:57:32,518][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:57:33,027][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:57:33,536][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:57:34,045][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:57:34,553][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:57:35,061][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:57:35,570][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:57:36,078][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:57:36,586][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:57:37,094][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:57:37,602][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:57:38,110][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:57:38,620][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:57:39,130][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:57:39,640][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:57:40,150][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:57:40,659][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:57:41,167][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:57:41,676][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:57:42,184][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:57:42,692][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:57:43,200][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:57:43,709][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:57:44,218][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:57:44,726][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:57:45,235][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:57:45,744][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:57:46,252][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:57:46,760][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:57:47,270][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:57:47,779][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:57:48,286][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:57:48,794][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:57:49,303][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:57:49,812][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21734 tokens. [2026-03-25 23:57:50,462][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-25 23:57:51,199][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:57:51,201][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:57:51,203][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:57:52,030][__main__][INFO] - Iteration 384 took 1m 16s (10.01% Gen, 88.91% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 25m 28s. Estimated total time: 63h 48m 7s. Time estimates for 10 more iterations: 12m 45s, 100 more iterations: 2h 7m 36s, 500 more iterations: 10h 38m 1s. [2026-03-25 23:57:52,032][__main__][INFO] - Starting iteration 384. [2026-03-25 23:57:52,434][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:57:52,435][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:57:59,292][__main__][INFO] - Number of regex retries in iteration 384: 0 [2026-03-25 23:57:59,292][__main__][INFO] - agents played in iteration 384 are Bob, Alice [2026-03-25 23:58:00,241][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:58:00,861][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:58:01,326][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:58:01,840][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:58:02,349][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:58:02,858][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:58:03,366][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:58:03,875][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:58:04,383][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:58:04,890][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:58:05,398][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:58:05,907][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:58:06,415][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:58:06,922][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:58:07,431][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:58:07,940][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:58:08,447][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:58:08,955][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:58:09,464][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:58:09,972][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:58:10,481][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:58:10,990][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:58:11,498][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:58:12,006][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:58:12,514][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:58:13,022][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:58:13,533][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:58:14,042][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:58:14,550][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:58:15,058][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:58:15,567][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:58:16,076][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:58:16,583][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:58:17,093][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:58:17,601][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:58:18,109][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:58:18,618][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:58:19,127][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:58:19,636][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:58:20,145][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:58:20,653][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:58:21,162][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:58:21,670][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:58:22,178][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:58:22,687][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:58:23,196][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:58:23,704][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:58:24,213][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:58:24,721][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:58:25,229][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:58:25,739][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:58:26,247][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:58:26,756][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:58:27,264][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:58:27,772][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:58:28,279][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:58:28,788][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:58:29,297][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:58:29,810][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:58:30,321][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:58:30,831][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:58:31,342][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:58:31,852][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:58:32,363][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:58:32,873][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:58:33,383][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:58:33,892][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:58:34,401][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:58:34,908][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:58:35,416][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:58:35,926][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:58:36,435][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:58:36,943][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:58:37,452][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:58:37,960][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:58:38,468][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:58:38,976][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:58:39,483][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:58:39,992][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:58:40,501][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:58:41,010][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:58:41,518][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:58:42,028][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:58:42,536][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:58:43,044][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:58:43,553][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-25 23:58:44,061][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-25 23:58:44,569][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-25 23:58:45,077][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-25 23:58:45,586][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-25 23:58:46,095][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-25 23:58:46,603][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-25 23:58:47,112][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-25 23:58:47,621][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-25 23:58:48,130][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-25 23:58:48,639][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-25 23:58:49,148][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-25 23:58:49,658][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-25 23:58:50,166][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-25 23:58:50,674][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-25 23:58:51,182][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-25 23:58:51,690][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-25 23:58:52,199][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-25 23:58:52,708][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-25 23:58:53,218][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-25 23:58:53,727][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-25 23:58:54,234][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-25 23:58:54,743][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-25 23:58:55,251][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-25 23:58:55,759][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-25 23:58:56,267][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-25 23:58:56,775][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-25 23:58:57,283][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-25 23:58:57,792][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-25 23:58:58,299][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-25 23:58:58,810][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-25 23:58:59,319][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-25 23:58:59,828][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-25 23:59:00,337][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-25 23:59:00,845][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-25 23:59:01,353][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-25 23:59:01,862][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-25 23:59:02,373][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-25 23:59:02,884][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-25 23:59:03,394][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-25 23:59:03,905][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-25 23:59:04,415][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-25 23:59:04,927][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-25 23:59:05,438][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-25 23:59:05,951][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-25 23:59:06,614][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.36%, Current % of VRAM taken: 60.71%, Block Peak % of device VRAM: 62.60%, ΔTime: 00:01:05 [2026-03-25 23:59:07,358][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-25 23:59:07,361][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-25 23:59:07,362][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-25 23:59:08,078][__main__][INFO] - Iteration 385 took 1m 15s (9.07% Gen, 89.99% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 38m 18s. Estimated total time: 63h 2m 13s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 4s, 500 more iterations: 10h 30m 22s. [2026-03-25 23:59:08,080][__main__][INFO] - Starting iteration 385. [2026-03-25 23:59:08,483][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-25 23:59:08,484][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-25 23:59:15,256][__main__][INFO] - Number of regex retries in iteration 385: 0 [2026-03-25 23:59:15,257][__main__][INFO] - agents played in iteration 385 are Bob, Alice [2026-03-25 23:59:16,214][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-25 23:59:16,839][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-25 23:59:17,304][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-25 23:59:17,819][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-25 23:59:18,330][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-25 23:59:18,840][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-25 23:59:19,350][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-25 23:59:19,859][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-25 23:59:20,369][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-25 23:59:20,878][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-25 23:59:21,385][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-25 23:59:21,891][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-25 23:59:22,398][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-25 23:59:22,906][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-25 23:59:23,413][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-25 23:59:23,920][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-25 23:59:24,430][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-25 23:59:24,938][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-25 23:59:25,447][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-25 23:59:25,954][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-25 23:59:26,460][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-25 23:59:26,970][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-25 23:59:27,479][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-25 23:59:27,989][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-25 23:59:28,497][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-25 23:59:29,005][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-25 23:59:29,516][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-25 23:59:30,024][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-25 23:59:30,532][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-25 23:59:31,041][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-25 23:59:31,549][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-25 23:59:32,057][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-25 23:59:32,566][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-25 23:59:33,075][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-25 23:59:33,583][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-25 23:59:34,091][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-25 23:59:34,600][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-25 23:59:35,108][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-25 23:59:35,616][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-25 23:59:36,125][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-25 23:59:36,633][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-25 23:59:37,142][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-25 23:59:37,650][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-25 23:59:38,159][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-25 23:59:38,667][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-25 23:59:39,176][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-25 23:59:39,684][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-25 23:59:40,193][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-25 23:59:40,701][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-25 23:59:41,211][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-25 23:59:41,721][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-25 23:59:42,230][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-25 23:59:42,739][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-25 23:59:43,247][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-25 23:59:43,755][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-25 23:59:44,264][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-25 23:59:44,772][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-25 23:59:45,280][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-25 23:59:45,789][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-25 23:59:46,298][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-25 23:59:46,807][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-25 23:59:47,316][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-25 23:59:47,824][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-25 23:59:48,333][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-25 23:59:48,842][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-25 23:59:49,350][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-25 23:59:49,860][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-25 23:59:50,367][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-25 23:59:50,876][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-25 23:59:51,386][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-25 23:59:51,897][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-25 23:59:52,408][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-25 23:59:52,916][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-25 23:59:53,426][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-25 23:59:53,934][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-25 23:59:54,441][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-25 23:59:54,951][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-25 23:59:55,460][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-25 23:59:55,970][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-25 23:59:56,478][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-25 23:59:56,987][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-25 23:59:57,496][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-25 23:59:58,004][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-25 23:59:58,513][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-25 23:59:59,021][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-25 23:59:59,531][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:00:00,039][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:00:00,548][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:00:01,059][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:00:01,569][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:00:02,078][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:00:02,588][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:00:03,098][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:00:03,608][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:00:04,117][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:00:04,628][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:00:05,138][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:00:05,649][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:00:06,157][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:00:06,667][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:00:07,176][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:00:07,685][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:00:08,194][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:00:08,702][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:00:09,212][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:00:09,721][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:00:10,231][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:00:10,741][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:00:11,250][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:00:11,759][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:00:12,269][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:00:12,778][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:00:13,289][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:00:13,800][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:00:14,309][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:00:14,818][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:00:15,328][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:00:15,839][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:00:16,348][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:00:16,857][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:00:17,368][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:00:17,877][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:00:18,385][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:00:18,895][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:00:19,404][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:00:19,914][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:00:20,423][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:00:20,933][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:00:21,441][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:00:21,950][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 00:00:22,613][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-26 00:00:23,359][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:00:23,361][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:00:23,363][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:00:24,123][__main__][INFO] - Iteration 386 took 1m 15s (8.95% Gen, 90.04% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 36m 52s. Estimated total time: 63h 2m 2s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 4s, 500 more iterations: 10h 30m 20s. [2026-03-26 00:00:24,126][__main__][INFO] - Starting iteration 386. [2026-03-26 00:00:24,529][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:00:24,530][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:00:27,655][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:00:32,084][__main__][INFO] - Number of regex retries in iteration 386: 1 [2026-03-26 00:00:32,085][__main__][INFO] - agents played in iteration 386 are Bob, Alice [2026-03-26 00:00:33,049][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:00:33,681][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:00:34,146][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:00:34,662][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:00:35,170][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:00:35,678][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:00:36,187][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:00:36,695][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:00:37,204][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:00:37,712][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:00:38,220][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:00:38,728][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:00:39,236][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:00:39,745][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:00:40,253][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:00:40,760][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:00:41,269][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:00:41,776][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:00:42,284][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:00:42,793][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:00:43,300][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:00:43,813][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:00:44,322][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:00:44,831][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:00:45,340][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:00:45,850][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:00:46,359][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:00:46,868][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:00:47,377][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:00:47,885][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:00:48,394][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:00:48,902][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:00:49,412][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:00:49,922][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:00:50,431][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:00:50,939][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:00:51,449][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:00:51,957][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:00:52,465][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:00:52,973][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:00:53,482][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:00:53,991][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:00:54,499][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:00:55,008][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:00:55,517][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:00:56,026][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:00:56,536][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:00:57,045][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:00:57,553][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:00:58,061][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:00:58,570][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:00:59,078][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:00:59,586][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:01:00,094][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:01:00,601][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:01:01,110][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:01:01,618][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:01:02,126][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:01:02,635][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:01:03,144][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:01:03,653][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:01:04,161][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:01:04,671][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:01:05,180][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:01:05,689][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:01:06,196][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:01:06,706][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:01:07,216][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:01:07,724][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:01:08,234][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:01:08,742][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:01:09,251][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:01:09,760][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:01:10,271][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:01:10,779][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:01:11,287][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:01:11,795][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:01:12,305][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:01:12,813][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:01:13,321][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:01:13,830][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:01:14,340][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:01:14,848][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:01:15,358][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:01:15,867][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:01:16,376][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:01:16,883][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:01:17,392][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:01:17,901][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:01:18,410][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:01:18,918][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:01:19,426][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:01:19,935][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:01:20,444][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:01:20,952][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:01:21,460][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:01:21,968][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:01:22,477][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:01:22,984][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:01:23,492][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:01:24,000][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:01:24,509][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:01:25,017][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:01:25,527][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:01:26,035][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:01:26,543][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:01:27,053][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:01:27,562][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:01:28,071][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:01:28,581][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:01:29,091][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:01:29,599][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:01:30,109][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:01:30,617][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:01:31,126][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:01:31,635][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:01:32,144][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:01:32,653][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:01:33,161][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:01:33,670][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:01:34,178][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:01:34,686][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:01:35,195][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:01:35,704][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:01:36,213][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:01:36,721][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:01:37,230][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:01:37,739][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:01:38,248][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:01:38,757][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-26 00:01:39,432][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.23%, ΔTime: 00:01:05 [2026-03-26 00:01:40,206][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:01:40,211][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:01:40,213][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:01:40,944][__main__][INFO] - Iteration 387 took 1m 16s (9.89% Gen, 89.15% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 14m 21s. Estimated total time: 63h 40m 49s. Time estimates for 10 more iterations: 12m 44s, 100 more iterations: 2h 7m 21s, 500 more iterations: 10h 36m 48s. [2026-03-26 00:01:40,946][__main__][INFO] - Starting iteration 387. [2026-03-26 00:01:41,348][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:01:41,349][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:01:48,577][__main__][INFO] - Number of regex retries in iteration 387: 0 [2026-03-26 00:01:48,577][__main__][INFO] - agents played in iteration 387 are Bob, Alice [2026-03-26 00:01:49,535][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:01:50,169][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:01:50,633][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:01:51,148][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:01:51,659][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:01:52,167][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:01:52,676][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:01:53,186][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:01:53,695][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:01:54,204][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:01:54,712][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:01:55,220][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:01:55,728][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:01:56,237][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:01:56,746][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:01:57,254][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:01:57,762][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:01:58,270][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:01:58,782][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:01:59,293][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:01:59,802][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:02:00,312][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:02:00,823][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:02:01,333][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:02:01,844][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:02:02,355][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:02:02,865][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:02:03,374][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:02:03,884][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:02:04,393][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:02:04,902][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:02:05,411][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:02:05,920][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:02:06,430][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:02:06,938][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:02:07,446][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:02:07,956][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:02:08,464][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:02:08,972][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:02:09,481][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:02:09,989][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:02:10,498][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:02:11,007][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:02:11,516][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:02:12,026][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:02:12,535][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:02:13,045][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:02:13,554][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:02:14,064][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:02:14,572][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:02:15,081][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:02:15,592][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:02:16,102][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:02:16,613][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:02:17,123][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:02:17,638][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:02:18,155][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:02:18,667][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:02:19,187][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:02:19,704][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:02:20,216][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:02:20,728][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:02:21,241][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:02:21,754][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:02:22,267][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:02:22,779][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:02:23,291][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:02:23,802][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:02:24,314][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:02:24,825][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:02:25,336][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:02:25,847][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:02:26,358][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:02:26,869][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:02:27,379][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:02:27,889][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:02:28,400][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:02:28,911][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:02:29,420][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:02:29,931][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:02:30,442][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:02:30,952][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:02:31,463][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:02:31,974][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:02:32,484][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:02:32,995][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:02:33,507][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:02:34,017][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:02:34,528][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:02:35,039][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:02:35,550][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:02:36,060][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:02:36,570][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:02:37,080][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:02:37,589][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:02:38,098][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:02:38,608][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:02:39,119][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:02:39,628][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:02:40,138][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:02:40,648][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:02:41,157][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:02:41,665][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:02:42,174][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:02:42,684][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:02:43,193][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:02:43,702][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:02:44,213][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:02:44,722][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:02:45,233][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:02:45,742][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:02:46,252][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:02:46,761][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:02:47,271][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:02:47,781][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:02:48,291][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:02:48,801][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:02:49,311][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:02:49,821][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:02:50,331][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:02:50,840][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:02:51,352][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:02:51,862][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:02:52,371][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:02:52,880][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:02:53,390][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:02:53,899][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:02:54,409][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:02:54,918][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:02:55,429][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-26 00:02:56,107][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 00:02:56,852][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:02:56,854][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:02:56,856][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:02:57,595][__main__][INFO] - Iteration 388 took 1m 16s (9.48% Gen, 89.55% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 4m 37s. Estimated total time: 63h 32m 22s. Time estimates for 10 more iterations: 12m 42s, 100 more iterations: 2h 7m 4s, 500 more iterations: 10h 35m 23s. [2026-03-26 00:02:57,598][__main__][INFO] - Starting iteration 388. [2026-03-26 00:02:57,998][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:02:57,999][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:02:59,774][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:03:00,886][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:03:02,944][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:03:04,898][__main__][INFO] - Number of regex retries in iteration 388: 3 [2026-03-26 00:03:04,899][__main__][INFO] - agents played in iteration 388 are Bob, Alice [2026-03-26 00:03:05,852][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:03:06,497][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:03:06,963][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:03:07,477][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:03:07,987][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:03:08,496][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:03:09,008][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:03:09,517][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:03:10,029][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:03:10,539][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:03:11,052][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:03:11,563][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:03:12,075][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:03:12,587][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:03:13,099][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:03:13,612][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:03:14,124][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:03:14,637][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:03:15,146][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:03:15,655][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:03:16,163][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:03:16,672][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:03:17,180][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:03:17,689][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:03:18,198][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:03:18,708][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:03:19,218][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:03:19,728][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:03:20,237][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:03:20,747][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:03:21,257][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:03:21,766][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:03:22,274][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:03:22,784][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:03:23,294][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:03:23,803][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:03:24,312][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:03:24,822][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:03:25,332][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:03:25,841][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:03:26,352][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:03:26,863][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:03:27,372][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:03:27,881][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:03:28,391][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:03:28,899][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:03:29,409][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:03:29,918][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:03:30,428][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:03:30,937][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:03:31,451][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:03:31,961][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:03:32,470][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:03:32,981][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:03:33,493][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:03:34,003][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:03:34,514][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:03:35,025][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:03:35,537][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:03:36,049][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:03:36,568][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:03:37,082][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:03:37,594][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:03:38,107][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:03:38,622][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:03:39,134][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:03:39,646][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:03:40,158][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:03:40,669][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:03:41,181][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:03:41,692][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:03:42,204][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:03:42,716][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:03:43,227][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:03:43,741][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:03:44,254][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:03:44,768][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:03:45,281][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:03:45,794][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:03:46,308][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:03:46,820][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:03:47,334][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:03:47,844][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:03:48,353][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:03:48,863][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:03:49,373][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:03:49,881][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:03:50,393][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:03:50,901][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:03:51,411][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:03:51,921][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:03:52,432][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:03:52,941][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:03:53,451][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:03:53,960][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:03:54,470][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:03:54,979][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:03:55,488][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:03:55,999][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:03:56,510][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:03:57,020][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:03:57,531][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:03:58,041][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:03:58,551][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:03:59,062][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:03:59,572][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:04:00,081][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:04:00,590][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:04:01,098][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:04:01,608][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:04:02,117][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:04:02,627][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:04:03,136][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:04:03,645][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:04:04,154][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:04:04,662][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:04:05,170][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:04:05,678][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:04:06,187][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:04:06,695][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:04:07,203][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:04:07,710][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:04:08,219][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:04:08,728][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:04:09,239][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:04:09,750][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:04:10,260][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:04:10,769][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:04:11,278][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:04:11,788][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 00:04:12,461][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.65%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:05 [2026-03-26 00:04:13,211][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:04:13,214][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:04:13,215][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:04:13,987][__main__][INFO] - Iteration 389 took 1m 15s (9.08% Gen, 89.90% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 50m 28s. Estimated total time: 63h 19m 29s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 38s, 500 more iterations: 10h 33m 14s. [2026-03-26 00:04:13,990][__main__][INFO] - Starting iteration 389. [2026-03-26 00:04:14,389][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:04:14,390][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:04:21,866][__main__][INFO] - Number of regex retries in iteration 389: 0 [2026-03-26 00:04:21,867][__main__][INFO] - agents played in iteration 389 are Bob, Alice [2026-03-26 00:04:22,821][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:04:23,428][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:04:23,893][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:04:24,406][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:04:24,914][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:04:25,422][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:04:25,931][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:04:26,440][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:04:26,948][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:04:27,456][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:04:27,968][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:04:28,477][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:04:28,985][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:04:29,495][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:04:30,005][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:04:30,516][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:04:31,027][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:04:31,538][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:04:32,047][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:04:32,556][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:04:33,067][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:04:33,576][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:04:34,085][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:04:34,593][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:04:35,102][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:04:35,611][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:04:36,122][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:04:36,634][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:04:37,145][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:04:37,656][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:04:38,166][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:04:38,677][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:04:39,188][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:04:39,699][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:04:40,209][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:04:40,717][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:04:41,225][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:04:41,733][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:04:42,242][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:04:42,750][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:04:43,258][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:04:43,766][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:04:44,275][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:04:44,783][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:04:45,291][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:04:45,800][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:04:46,309][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:04:46,818][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:04:47,327][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:04:47,837][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:04:48,341][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:04:48,846][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:04:49,351][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:04:49,856][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:04:50,360][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:04:50,866][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:04:51,372][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:04:51,875][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:04:52,384][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:04:52,892][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:04:53,400][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:04:53,910][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:04:54,418][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:04:54,926][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:04:55,435][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:04:55,942][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:04:56,450][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:04:56,959][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:04:57,467][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:04:57,975][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:04:58,484][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:04:58,991][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:04:59,499][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:05:00,008][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:05:00,516][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:05:01,025][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:05:01,533][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:05:02,043][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:05:02,553][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:05:03,061][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:05:03,569][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:05:04,078][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:05:04,587][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:05:05,095][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:05:05,603][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:05:06,111][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:05:06,619][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:05:07,128][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:05:07,636][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:05:08,145][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:05:08,654][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:05:09,164][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:05:09,673][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:05:10,182][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:05:10,692][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:05:11,200][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:05:11,710][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:05:12,219][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:05:12,728][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:05:13,236][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:05:13,745][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:05:14,253][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:05:14,761][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:05:15,271][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:05:15,779][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:05:16,287][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:05:16,794][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:05:17,303][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:05:17,812][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:05:18,321][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:05:18,830][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:05:19,339][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:05:19,847][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:05:20,355][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:05:20,860][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:05:21,365][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:05:21,870][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:05:22,374][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:05:22,879][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:05:23,386][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:05:23,893][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:05:24,399][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:05:24,908][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:05:25,418][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:05:25,928][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:05:26,439][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:05:26,948][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:05:27,457][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:05:27,966][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:05:28,475][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 00:05:29,147][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 00:05:29,904][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:05:29,906][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:05:29,908][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:05:30,578][__main__][INFO] - Iteration 390 took 1m 16s (9.81% Gen, 89.30% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 59m 8s. Estimated total time: 63h 29m 25s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 58s, 500 more iterations: 10h 34m 54s. [2026-03-26 00:05:30,580][__main__][INFO] - Starting iteration 390. [2026-03-26 00:05:30,986][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:05:30,986][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:05:37,549][__main__][INFO] - Number of regex retries in iteration 390: 0 [2026-03-26 00:05:37,550][__main__][INFO] - agents played in iteration 390 are Bob, Alice [2026-03-26 00:05:38,798][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:05:39,417][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:05:39,883][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:05:40,397][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:05:40,908][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:05:41,418][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:05:41,928][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:05:42,438][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:05:42,948][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:05:43,457][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:05:43,965][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:05:44,473][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:05:44,982][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:05:45,491][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:05:45,999][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:05:46,509][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:05:47,019][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:05:47,529][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:05:48,041][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:05:48,549][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:05:49,059][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:05:49,568][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:05:50,077][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:05:50,586][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:05:51,094][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:05:51,603][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:05:52,112][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:05:52,621][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:05:53,130][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:05:53,639][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:05:54,148][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:05:54,658][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:05:55,165][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:05:55,674][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:05:56,182][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:05:56,690][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:05:57,199][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:05:57,708][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:05:58,216][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:05:58,725][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:05:59,233][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:05:59,743][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:06:00,251][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:06:00,759][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:06:01,269][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:06:01,778][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:06:02,286][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:06:02,794][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:06:03,302][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:06:03,811][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:06:04,318][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:06:04,826][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:06:05,333][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:06:05,841][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:06:06,348][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:06:06,855][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:06:07,362][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:06:07,869][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:06:08,376][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:06:08,884][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:06:09,391][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:06:09,899][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:06:10,407][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:06:10,914][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:06:11,421][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:06:11,930][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:06:12,439][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:06:12,950][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:06:13,461][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:06:13,970][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:06:14,479][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:06:14,989][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:06:15,499][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:06:16,009][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:06:16,518][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:06:17,029][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:06:17,540][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:06:18,050][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:06:18,560][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:06:19,071][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:06:19,581][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:06:20,091][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:06:20,600][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:06:21,111][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:06:21,620][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:06:22,131][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:06:22,642][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:06:23,153][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:06:23,662][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:06:24,172][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:06:24,682][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:06:25,191][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:06:25,700][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:06:26,209][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:06:26,716][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:06:27,226][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:06:27,736][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:06:28,245][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:06:28,755][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:06:29,264][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:06:29,778][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:06:30,288][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:06:30,797][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:06:31,306][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:06:31,816][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:06:32,325][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:06:32,836][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:06:33,347][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:06:33,858][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:06:34,380][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:06:34,891][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:06:35,403][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:06:35,915][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:06:36,426][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:06:36,935][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:06:37,445][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:06:37,954][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:06:38,464][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:06:38,973][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:06:39,482][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:06:39,992][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:06:40,501][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:06:41,010][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:06:41,519][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:06:42,029][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:06:42,538][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:06:43,050][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:06:43,559][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:06:44,068][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:06:44,577][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-26 00:06:45,233][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:05 [2026-03-26 00:06:45,983][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:06:45,985][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:06:45,987][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:06:46,850][__main__][INFO] - Iteration 391 took 1m 15s (8.65% Gen, 90.21% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 41m 41s. Estimated total time: 63h 13m 15s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 26s, 500 more iterations: 10h 32m 12s. [2026-03-26 00:06:46,852][__main__][INFO] - Starting iteration 391. [2026-03-26 00:06:47,253][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:06:47,254][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:06:52,973][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:06:54,575][__main__][INFO] - Number of regex retries in iteration 391: 1 [2026-03-26 00:06:54,576][__main__][INFO] - agents played in iteration 391 are Bob, Alice [2026-03-26 00:06:55,544][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:06:56,174][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:06:56,640][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:06:57,153][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:06:57,661][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:06:58,170][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:06:58,679][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:06:59,188][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:06:59,695][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:07:00,205][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:07:00,714][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:07:01,222][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:07:01,731][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:07:02,241][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:07:02,751][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:07:03,261][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:07:03,770][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:07:04,279][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:07:04,787][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:07:05,294][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:07:05,802][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:07:06,310][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:07:06,817][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:07:07,326][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:07:07,834][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:07:08,343][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:07:08,854][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:07:09,363][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:07:09,872][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:07:10,381][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:07:10,889][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:07:11,398][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:07:11,907][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:07:12,417][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:07:12,925][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:07:13,435][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:07:13,944][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:07:14,454][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:07:14,962][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:07:15,471][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:07:15,980][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:07:16,489][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:07:16,998][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:07:17,508][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:07:18,018][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:07:18,528][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:07:19,038][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:07:19,547][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:07:20,056][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:07:20,564][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:07:21,073][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:07:21,581][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:07:22,090][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:07:22,600][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:07:23,110][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:07:23,620][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:07:24,129][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:07:24,638][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:07:25,148][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:07:25,657][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:07:26,165][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:07:26,674][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:07:27,182][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:07:27,690][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:07:28,199][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:07:28,708][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:07:29,218][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:07:29,729][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:07:30,240][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:07:30,750][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:07:31,260][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:07:31,771][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:07:32,281][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:07:32,792][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:07:33,300][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:07:33,810][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:07:34,319][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:07:34,830][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:07:35,338][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:07:35,848][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:07:36,357][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:07:36,866][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:07:37,376][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:07:37,885][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:07:38,393][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:07:38,904][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:07:39,413][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:07:39,921][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:07:40,432][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:07:40,942][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:07:41,452][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:07:41,962][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:07:42,472][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:07:42,981][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:07:43,491][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:07:44,000][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:07:44,511][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:07:45,022][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:07:45,532][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:07:46,041][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:07:46,550][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:07:47,060][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:07:47,571][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:07:48,079][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:07:48,589][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:07:49,099][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:07:49,608][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:07:50,118][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:07:50,628][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:07:51,137][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:07:51,647][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:07:52,157][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:07:52,666][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:07:53,175][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:07:53,684][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:07:54,193][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:07:54,702][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:07:55,210][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:07:55,719][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:07:56,230][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:07:56,739][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:07:57,249][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:07:57,758][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:07:58,268][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:07:58,776][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:07:59,285][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:07:59,794][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:08:00,302][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:08:00,816][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:08:01,327][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21725 tokens. [2026-03-26 00:08:01,990][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-26 00:08:02,747][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:08:02,749][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:08:02,751][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:08:03,508][__main__][INFO] - Iteration 392 took 1m 16s (9.60% Gen, 89.40% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 59m 56s. Estimated total time: 63h 32m 47s. Time estimates for 10 more iterations: 12m 42s, 100 more iterations: 2h 7m 5s, 500 more iterations: 10h 35m 27s. [2026-03-26 00:08:03,510][__main__][INFO] - Starting iteration 392. [2026-03-26 00:08:03,913][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:08:03,914][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:08:10,332][__main__][INFO] - Number of regex retries in iteration 392: 0 [2026-03-26 00:08:10,333][__main__][INFO] - agents played in iteration 392 are Bob, Alice [2026-03-26 00:08:11,298][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:08:11,928][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:08:12,392][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:08:12,904][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:08:13,411][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:08:13,920][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:08:14,429][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:08:14,937][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:08:15,445][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:08:15,953][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:08:16,465][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:08:16,974][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:08:17,484][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:08:17,993][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:08:18,502][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:08:19,012][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:08:19,521][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:08:20,031][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:08:20,540][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:08:21,051][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:08:21,561][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:08:22,070][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:08:22,579][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:08:23,089][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:08:23,598][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:08:24,107][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:08:24,616][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:08:25,125][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:08:25,634][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:08:26,142][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:08:26,651][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:08:27,161][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:08:27,670][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:08:28,178][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:08:28,688][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:08:29,196][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:08:29,703][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:08:30,210][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:08:30,719][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:08:31,227][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:08:31,735][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:08:32,242][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:08:32,751][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:08:33,260][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:08:33,768][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:08:34,277][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:08:34,786][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:08:35,294][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:08:35,801][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:08:36,312][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:08:36,822][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:08:37,330][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:08:37,839][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:08:38,348][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:08:38,856][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:08:39,364][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:08:39,872][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:08:40,380][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:08:40,888][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:08:41,394][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:08:41,900][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:08:42,411][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:08:42,919][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:08:43,429][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:08:43,937][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:08:44,446][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:08:44,953][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:08:45,461][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:08:45,970][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:08:46,478][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:08:46,985][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:08:47,492][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:08:47,998][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:08:48,505][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:08:49,013][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:08:49,521][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:08:50,031][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:08:50,542][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:08:51,050][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:08:51,559][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:08:52,069][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:08:52,577][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:08:53,084][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:08:53,591][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:08:54,098][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:08:54,606][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:08:55,114][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:08:55,621][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:08:56,129][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:08:56,637][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:08:57,145][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:08:57,654][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:08:58,162][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:08:58,670][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:08:59,179][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:08:59,689][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:09:00,198][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:09:00,706][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:09:01,214][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:09:01,721][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:09:02,229][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:09:02,737][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:09:03,243][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:09:03,750][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:09:04,258][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:09:04,765][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:09:05,273][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:09:05,780][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:09:06,286][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:09:06,792][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:09:07,301][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:09:07,810][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:09:08,320][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:09:08,829][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:09:09,339][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:09:09,848][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:09:10,357][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:09:10,866][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:09:11,375][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:09:11,883][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:09:12,397][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:09:12,908][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:09:13,418][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:09:13,928][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:09:14,437][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:09:14,947][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:09:15,458][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:09:15,970][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:09:16,480][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:09:16,990][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-26 00:09:17,654][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.20%, ΔTime: 00:01:05 [2026-03-26 00:09:18,409][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:09:18,411][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:09:18,413][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:09:19,237][__main__][INFO] - Iteration 393 took 1m 15s (8.52% Gen, 90.38% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 12m 8s. Estimated total time: 62h 46m 14s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 32s, 500 more iterations: 10h 27m 42s. [2026-03-26 00:09:19,240][__main__][INFO] - Starting iteration 393. [2026-03-26 00:09:19,641][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:09:19,641][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:09:25,380][mllm.models.large_language_model_local][WARNING] - Response Propagation: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:09:26,927][__main__][INFO] - Number of regex retries in iteration 393: 1 [2026-03-26 00:09:26,928][__main__][INFO] - agents played in iteration 393 are Bob, Alice [2026-03-26 00:09:27,890][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:09:28,524][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:09:28,988][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:09:29,501][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:09:30,010][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:09:30,519][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:09:31,028][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:09:31,538][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:09:32,047][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:09:32,556][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:09:33,064][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:09:33,572][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:09:34,081][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:09:34,591][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:09:35,098][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:09:35,607][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:09:36,116][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:09:36,624][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:09:37,130][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:09:37,644][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:09:38,153][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:09:38,662][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:09:39,171][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:09:39,680][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:09:40,190][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:09:40,698][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:09:41,209][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:09:41,717][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:09:42,225][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:09:42,734][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:09:43,243][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:09:43,752][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:09:44,261][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:09:44,769][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:09:45,279][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:09:45,788][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:09:46,297][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:09:46,805][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:09:47,314][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:09:47,822][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:09:48,332][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:09:48,842][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:09:49,354][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:09:49,864][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:09:50,375][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:09:50,885][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:09:51,395][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:09:51,905][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:09:52,416][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:09:52,925][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:09:53,434][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:09:53,944][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:09:54,454][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:09:54,962][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:09:55,472][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:09:55,980][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:09:56,490][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:09:56,998][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:09:57,507][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:09:58,016][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:09:58,524][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:09:59,035][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:09:59,544][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:10:00,053][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:10:00,562][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:10:01,072][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:10:01,580][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:10:02,088][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:10:02,596][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:10:03,104][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:10:03,612][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:10:04,120][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:10:04,629][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:10:05,139][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:10:05,648][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:10:06,156][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:10:06,664][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:10:07,173][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:10:07,682][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:10:08,189][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:10:08,697][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:10:09,205][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:10:09,714][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:10:10,222][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:10:10,731][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:10:11,241][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:10:11,750][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:10:12,259][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:10:12,769][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:10:13,278][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:10:13,787][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:10:14,295][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:10:14,804][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:10:15,313][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:10:15,822][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:10:16,330][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:10:16,839][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:10:17,348][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:10:17,859][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:10:18,369][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:10:18,879][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:10:19,388][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:10:19,902][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:10:20,414][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:10:20,924][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:10:21,435][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:10:21,947][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:10:22,459][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:10:22,971][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:10:23,483][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:10:23,995][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:10:24,511][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:10:25,025][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:10:25,539][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:10:26,051][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:10:26,563][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:10:27,075][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:10:27,587][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:10:28,099][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:10:28,611][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:10:29,132][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:10:29,645][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:10:30,157][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:10:30,668][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:10:31,180][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:10:31,693][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:10:32,204][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:10:32,715][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:10:33,227][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:10:33,743][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21729 tokens. [2026-03-26 00:10:34,422][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-26 00:10:35,186][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:10:35,188][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:10:35,190][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:10:35,930][__main__][INFO] - Iteration 394 took 1m 16s (9.55% Gen, 89.48% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 59m 7s. Estimated total time: 63h 34m 30s. Time estimates for 10 more iterations: 12m 42s, 100 more iterations: 2h 7m 9s, 500 more iterations: 10h 35m 45s. [2026-03-26 00:10:35,932][__main__][INFO] - Starting iteration 394. [2026-03-26 00:10:36,335][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:10:36,336][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:10:43,117][__main__][INFO] - Number of regex retries in iteration 394: 0 [2026-03-26 00:10:43,117][__main__][INFO] - agents played in iteration 394 are Bob, Alice [2026-03-26 00:10:44,085][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:10:44,721][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:10:45,186][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:10:45,701][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:10:46,210][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:10:46,720][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:10:47,228][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:10:47,739][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:10:48,249][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:10:48,758][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:10:49,271][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:10:49,781][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:10:50,292][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:10:50,803][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:10:51,313][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:10:51,823][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:10:52,334][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:10:52,844][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:10:53,358][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:10:53,870][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:10:54,380][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:10:54,889][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:10:55,399][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:10:55,911][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:10:56,421][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:10:56,932][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:10:57,442][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:10:57,950][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:10:58,459][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:10:58,968][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:10:59,475][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:10:59,983][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:11:00,491][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:11:00,999][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:11:01,509][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:11:02,018][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:11:02,531][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:11:03,042][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:11:03,552][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:11:04,062][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:11:04,572][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:11:05,083][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:11:05,592][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:11:06,102][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:11:06,611][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:11:07,121][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:11:07,632][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:11:08,143][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:11:08,652][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:11:09,162][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:11:09,691][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:11:10,207][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:11:10,717][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:11:11,231][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:11:11,743][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:11:12,256][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:11:12,767][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:11:13,279][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:11:13,788][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:11:14,298][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:11:14,810][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:11:15,321][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:11:15,832][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:11:16,344][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:11:16,855][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:11:17,366][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:11:17,875][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:11:18,386][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:11:18,894][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:11:19,403][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:11:19,913][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:11:20,421][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:11:20,932][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:11:21,442][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:11:21,952][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:11:22,462][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:11:22,973][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:11:23,483][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:11:23,992][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:11:24,502][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:11:25,014][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:11:25,525][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:11:26,036][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:11:26,547][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:11:27,057][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:11:27,567][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:11:28,077][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:11:28,587][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:11:29,098][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:11:29,608][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:11:30,117][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:11:30,627][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:11:31,135][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:11:31,645][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:11:32,153][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:11:32,663][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:11:33,171][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:11:33,680][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:11:34,190][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:11:34,700][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:11:35,213][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:11:35,722][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:11:36,233][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:11:36,743][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:11:37,253][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:11:37,763][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:11:38,272][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:11:38,783][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:11:39,293][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:11:39,803][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:11:40,314][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:11:40,824][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:11:41,334][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:11:41,845][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:11:42,357][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:11:42,869][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:11:43,380][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:11:43,891][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:11:44,402][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:11:44,914][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:11:45,425][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:11:45,937][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:11:46,449][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:11:46,960][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:11:47,471][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:11:47,982][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:11:48,492][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:11:49,003][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:11:49,515][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:11:50,026][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 00:11:50,691][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.66%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-26 00:11:51,451][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:11:51,453][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:11:51,454][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:11:52,216][__main__][INFO] - Iteration 395 took 1m 15s (8.94% Gen, 90.06% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 37m 25s. Estimated total time: 63h 14m 4s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 28s, 500 more iterations: 10h 32m 20s. [2026-03-26 00:11:52,218][__main__][INFO] - Starting iteration 395. [2026-03-26 00:11:52,619][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:11:52,620][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:11:59,586][__main__][INFO] - Number of regex retries in iteration 395: 0 [2026-03-26 00:11:59,587][__main__][INFO] - agents played in iteration 395 are Bob, Alice [2026-03-26 00:12:00,550][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:12:01,174][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:12:01,643][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:12:02,158][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:12:02,667][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:12:03,177][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:12:03,686][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:12:04,195][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:12:04,704][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:12:05,214][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:12:05,722][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:12:06,230][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:12:06,740][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:12:07,249][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:12:07,758][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:12:08,266][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:12:08,774][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:12:09,282][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:12:09,795][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:12:10,304][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:12:10,814][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:12:11,323][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:12:11,834][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:12:12,344][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:12:12,854][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:12:13,363][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:12:13,871][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:12:14,380][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:12:14,888][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:12:15,397][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:12:15,905][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:12:16,414][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:12:16,923][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:12:17,433][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:12:17,937][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:12:18,443][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:12:18,950][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:12:19,458][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:12:19,962][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:12:20,469][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:12:20,975][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:12:21,483][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:12:21,993][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:12:22,502][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:12:23,011][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:12:23,520][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:12:24,030][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:12:24,538][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:12:25,046][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:12:25,554][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:12:26,063][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:12:26,571][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:12:27,079][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:12:27,589][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:12:28,098][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:12:28,606][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:12:29,115][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:12:29,625][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:12:30,133][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:12:30,641][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:12:31,150][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:12:31,659][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:12:32,167][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:12:32,675][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:12:33,181][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:12:33,690][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:12:34,199][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:12:34,708][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:12:35,217][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:12:35,727][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:12:36,235][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:12:36,743][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:12:37,252][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:12:37,762][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:12:38,270][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:12:38,778][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:12:39,287][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:12:39,793][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:12:40,301][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:12:40,810][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:12:41,319][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:12:41,829][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:12:42,338][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:12:42,849][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:12:43,359][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:12:43,868][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:12:44,377][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:12:44,888][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:12:45,397][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:12:45,907][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:12:46,416][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:12:46,924][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:12:47,432][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:12:47,940][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:12:48,450][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:12:48,958][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:12:49,465][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:12:49,974][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:12:50,482][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:12:50,990][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:12:51,497][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:12:52,004][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:12:52,512][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:12:53,021][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:12:53,527][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:12:54,036][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:12:54,544][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:12:55,054][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:12:55,562][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:12:56,071][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:12:56,580][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:12:57,088][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:12:57,597][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:12:58,106][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:12:58,614][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:12:59,122][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:12:59,632][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:13:00,141][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:13:00,650][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:13:01,160][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:13:01,667][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:13:02,176][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:13:02,684][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:13:03,193][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:13:03,700][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:13:04,210][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:13:04,718][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:13:05,226][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:13:05,739][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:13:06,249][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21601 tokens. [2026-03-26 00:13:06,906][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-26 00:13:07,656][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:13:07,658][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:13:07,660][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:13:08,389][__main__][INFO] - Iteration 396 took 1m 15s (9.20% Gen, 89.84% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 30m 39s. Estimated total time: 63h 8m 34s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 17s, 500 more iterations: 10h 31m 25s. [2026-03-26 00:13:08,392][__main__][INFO] - Starting iteration 396. [2026-03-26 00:13:08,794][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:13:08,795][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:13:10,601][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:13:11,170][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:13:15,823][__main__][INFO] - Number of regex retries in iteration 396: 2 [2026-03-26 00:13:15,824][__main__][INFO] - agents played in iteration 396 are Bob, Alice [2026-03-26 00:13:16,785][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:13:17,410][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:13:17,875][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:13:18,389][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:13:18,898][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:13:19,409][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:13:19,919][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:13:20,430][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:13:20,941][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:13:21,450][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:13:21,958][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:13:22,466][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:13:22,973][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:13:23,480][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:13:23,987][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:13:24,496][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:13:25,001][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:13:25,508][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:13:26,016][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:13:26,524][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:13:27,033][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:13:27,541][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:13:28,048][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:13:28,556][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:13:29,064][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:13:29,572][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:13:30,082][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:13:30,591][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:13:31,099][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:13:31,609][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:13:32,118][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:13:32,628][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:13:33,137][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:13:33,647][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:13:34,155][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:13:34,664][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:13:35,173][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:13:35,682][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:13:36,192][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:13:36,702][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:13:37,211][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:13:37,720][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:13:38,230][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:13:38,739][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:13:39,247][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:13:39,756][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:13:40,265][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:13:40,771][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:13:41,279][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:13:41,790][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:13:42,297][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:13:42,804][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:13:43,313][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:13:43,820][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:13:44,329][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:13:44,837][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:13:45,345][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:13:45,851][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:13:46,360][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:13:46,868][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:13:47,376][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:13:47,884][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:13:48,393][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:13:48,899][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:13:49,409][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:13:49,918][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:13:50,429][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:13:50,939][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:13:51,450][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:13:51,960][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:13:52,470][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:13:52,979][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:13:53,490][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:13:54,000][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:13:54,508][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:13:55,016][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:13:55,523][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:13:56,031][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:13:56,539][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:13:57,049][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:13:57,557][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:13:58,065][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:13:58,573][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:13:59,082][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:13:59,591][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:14:00,100][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:14:00,609][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:14:01,119][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:14:01,628][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:14:02,137][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:14:02,647][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:14:03,157][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:14:03,666][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:14:04,175][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:14:04,685][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:14:05,194][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:14:05,704][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:14:06,212][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:14:06,721][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:14:07,230][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:14:07,739][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:14:08,250][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:14:08,767][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:14:09,277][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:14:09,787][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:14:10,297][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:14:10,807][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:14:11,317][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:14:11,827][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:14:12,337][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:14:12,848][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:14:13,359][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:14:13,871][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:14:14,382][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:14:14,891][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:14:15,400][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:14:15,909][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:14:16,419][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:14:16,930][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:14:17,440][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:14:17,953][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:14:18,463][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:14:18,973][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:14:19,483][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:14:19,993][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:14:20,503][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:14:21,013][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:14:21,523][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:14:22,037][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:14:22,547][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21736 tokens. [2026-03-26 00:14:23,218][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 00:14:23,973][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:14:23,976][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:14:23,977][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:14:24,797][__main__][INFO] - Iteration 397 took 1m 16s (9.25% Gen, 89.67% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 41m 0s. Estimated total time: 63h 20m 12s. Time estimates for 10 more iterations: 12m 40s, 100 more iterations: 2h 6m 40s, 500 more iterations: 10h 33m 22s. [2026-03-26 00:14:24,800][__main__][INFO] - Starting iteration 397. [2026-03-26 00:14:25,202][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:14:25,203][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:14:31,837][__main__][INFO] - Number of regex retries in iteration 397: 0 [2026-03-26 00:14:31,838][__main__][INFO] - agents played in iteration 397 are Bob, Alice [2026-03-26 00:14:32,807][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:14:33,439][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:14:33,905][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:14:34,419][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:14:34,929][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:14:35,440][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:14:35,948][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:14:36,458][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:14:36,968][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:14:37,478][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:14:37,985][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:14:38,493][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:14:39,002][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:14:39,509][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:14:40,016][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:14:40,524][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:14:41,032][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:14:41,540][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:14:42,050][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:14:42,558][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:14:43,067][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:14:43,577][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:14:44,086][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:14:44,594][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:14:45,103][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:14:45,613][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:14:46,121][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:14:46,630][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:14:47,139][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:14:47,647][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:14:48,154][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:14:48,662][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:14:49,169][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:14:49,676][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:14:50,186][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:14:50,694][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:14:51,202][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:14:51,711][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:14:52,220][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:14:52,728][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:14:53,237][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:14:53,746][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:14:54,256][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:14:54,764][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:14:55,273][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:14:55,782][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:14:56,292][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:14:56,801][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:14:57,310][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:14:57,819][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:14:58,328][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:14:58,838][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:14:59,348][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:14:59,858][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:15:00,367][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:15:00,876][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:15:01,385][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:15:01,894][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:15:02,402][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:15:02,911][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:15:03,419][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:15:03,928][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:15:04,437][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:15:04,945][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:15:05,453][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:15:05,961][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:15:06,471][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:15:06,981][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:15:07,490][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:15:08,000][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:15:08,510][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:15:09,019][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:15:09,528][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:15:10,038][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:15:10,547][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:15:11,055][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:15:11,563][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:15:12,072][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:15:12,580][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:15:13,088][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:15:13,595][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:15:14,102][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:15:14,612][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:15:15,121][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:15:15,631][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:15:16,140][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:15:16,650][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:15:17,159][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:15:17,668][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:15:18,177][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:15:18,685][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:15:19,193][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:15:19,701][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:15:20,212][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:15:20,721][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:15:21,229][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:15:21,737][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:15:22,246][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:15:22,755][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:15:23,263][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:15:23,770][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:15:24,279][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:15:24,787][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:15:25,295][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:15:25,801][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:15:26,310][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:15:26,820][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:15:27,328][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:15:27,836][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:15:28,345][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:15:28,854][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:15:29,362][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:15:29,872][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:15:30,381][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:15:30,890][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:15:31,398][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:15:31,907][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:15:32,417][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:15:32,925][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:15:33,435][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:15:33,944][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:15:34,454][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:15:34,961][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:15:35,471][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:15:35,980][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:15:36,489][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:15:36,997][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:15:37,506][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:15:38,014][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:15:38,522][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21747 tokens. [2026-03-26 00:15:39,181][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-26 00:15:39,930][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:15:39,932][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:15:39,934][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:15:40,821][__main__][INFO] - Iteration 398 took 1m 15s (8.77% Gen, 90.05% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 20m 33s. Estimated total time: 63h 1m 0s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 2s, 500 more iterations: 10h 30m 10s. [2026-03-26 00:15:40,824][__main__][INFO] - Starting iteration 398. [2026-03-26 00:15:41,241][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:15:41,242][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:15:48,303][__main__][INFO] - Number of regex retries in iteration 398: 0 [2026-03-26 00:15:48,304][__main__][INFO] - agents played in iteration 398 are Bob, Alice [2026-03-26 00:15:49,265][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:15:49,897][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:15:50,361][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:15:50,873][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:15:51,381][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:15:51,889][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:15:52,397][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:15:52,905][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:15:53,413][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:15:53,921][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:15:54,430][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:15:54,940][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:15:55,448][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:15:55,956][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:15:56,465][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:15:56,973][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:15:57,481][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:15:57,990][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:15:58,501][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:15:59,012][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:15:59,521][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:16:00,031][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:16:00,541][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:16:01,051][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:16:01,560][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:16:02,070][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:16:02,580][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:16:03,088][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:16:03,597][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:16:04,107][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:16:04,616][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:16:05,125][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:16:05,633][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:16:06,142][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:16:06,654][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:16:07,164][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:16:07,673][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:16:08,182][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:16:08,693][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:16:09,202][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:16:09,712][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:16:10,222][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:16:10,731][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:16:11,240][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:16:11,749][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:16:12,258][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:16:12,766][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:16:13,276][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:16:13,784][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:16:14,294][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:16:14,801][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:16:15,309][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:16:15,818][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:16:16,327][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:16:16,837][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:16:17,345][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:16:17,853][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:16:18,361][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:16:18,870][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:16:19,380][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:16:19,890][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:16:20,398][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:16:20,908][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:16:21,418][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:16:21,926][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:16:22,435][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:16:22,944][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:16:23,453][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:16:23,961][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:16:24,471][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:16:24,980][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:16:25,488][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:16:25,996][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:16:26,505][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:16:27,013][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:16:27,521][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:16:28,031][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:16:28,540][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:16:29,048][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:16:29,555][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:16:30,063][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:16:30,571][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:16:31,080][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:16:31,589][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:16:32,098][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:16:32,608][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:16:33,118][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:16:33,629][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:16:34,140][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:16:34,649][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:16:35,158][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:16:35,668][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:16:36,177][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:16:36,685][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:16:37,194][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:16:37,702][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:16:38,211][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:16:38,721][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:16:39,231][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:16:39,741][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:16:40,250][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:16:40,760][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:16:41,271][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:16:41,781][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:16:42,292][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:16:42,800][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:16:43,310][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:16:43,819][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:16:44,328][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:16:44,837][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:16:45,346][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:16:45,854][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:16:46,362][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:16:46,871][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:16:47,380][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:16:47,888][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:16:48,396][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:16:48,904][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:16:49,413][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:16:49,921][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:16:50,430][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:16:50,940][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:16:51,449][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:16:51,957][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:16:52,468][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:16:52,979][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:16:53,488][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:16:53,997][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:16:54,506][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:16:55,016][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 00:16:55,680][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-26 00:16:56,428][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:16:56,431][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:16:56,432][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:16:57,131][__main__][INFO] - Iteration 399 took 1m 15s (9.30% Gen, 89.77% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 32m 47s. Estimated total time: 63h 14m 31s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 29s, 500 more iterations: 10h 32m 25s. [2026-03-26 00:16:57,133][__main__][INFO] - Starting iteration 399. [2026-03-26 00:16:57,537][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:16:57,538][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:16:58,184][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:17:04,568][__main__][INFO] - Number of regex retries in iteration 399: 1 [2026-03-26 00:17:04,569][__main__][INFO] - agents played in iteration 399 are Bob, Alice [2026-03-26 00:17:05,529][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:17:06,152][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:17:06,618][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:17:07,133][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:17:07,643][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:17:08,153][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:17:08,663][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:17:09,173][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:17:09,683][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:17:10,192][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:17:10,700][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:17:11,209][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:17:11,717][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:17:12,226][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:17:12,734][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:17:13,242][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:17:13,752][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:17:14,260][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:17:14,769][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:17:15,277][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:17:15,786][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:17:16,294][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:17:16,802][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:17:17,310][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:17:17,818][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:17:18,327][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:17:18,836][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:17:19,344][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:17:19,852][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:17:20,361][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:17:20,869][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:17:21,377][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:17:21,885][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:17:22,393][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:17:22,901][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:17:23,412][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:17:23,921][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:17:24,429][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:17:24,938][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:17:25,446][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:17:25,955][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:17:26,463][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:17:26,972][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:17:27,481][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:17:27,990][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:17:28,499][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:17:29,012][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:17:29,521][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:17:30,030][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:17:30,540][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:17:31,048][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:17:31,555][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:17:32,063][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:17:32,571][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:17:33,079][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:17:33,587][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:17:34,094][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:17:34,601][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:17:35,111][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:17:35,622][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:17:36,133][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:17:36,643][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:17:37,153][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:17:37,662][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:17:38,172][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:17:38,681][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:17:39,191][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:17:39,700][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:17:40,213][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:17:40,723][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:17:41,234][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:17:41,744][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:17:42,253][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:17:42,763][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:17:43,272][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:17:43,780][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:17:44,288][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:17:44,796][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:17:45,304][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:17:45,813][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:17:46,322][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:17:46,831][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:17:47,339][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:17:47,851][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:17:48,360][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:17:48,870][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:17:49,377][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:17:49,885][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:17:50,393][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:17:50,900][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:17:51,412][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:17:51,920][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:17:52,428][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:17:52,937][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:17:53,445][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:17:53,955][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:17:54,463][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:17:54,971][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:17:55,480][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:17:55,989][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:17:56,497][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:17:57,006][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:17:57,515][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:17:58,024][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:17:58,534][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:17:59,044][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:17:59,552][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:18:00,060][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:18:00,570][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:18:01,080][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:18:01,588][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:18:02,097][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:18:02,605][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:18:03,113][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:18:03,621][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:18:04,128][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:18:04,635][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:18:05,143][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:18:05,650][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:18:06,157][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:18:06,663][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:18:07,171][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:18:07,681][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:18:08,190][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:18:08,699][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:18:09,209][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:18:09,719][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:18:10,230][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:18:10,740][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:18:11,250][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 00:18:11,900][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.65%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 00:18:12,641][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:18:12,644][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:18:12,645][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:18:13,385][__main__][INFO] - Iteration 400 took 1m 15s (9.27% Gen, 89.75% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 29m 24s. Estimated total time: 63h 12m 24s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 24s, 500 more iterations: 10h 32m 4s. [2026-03-26 00:18:13,387][__main__][INFO] - Starting iteration 400. [2026-03-26 00:18:13,787][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 7 and human policies 1. [2026-03-26 00:18:13,788][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:18:14,433][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:18:21,653][__main__][INFO] - Number of regex retries in iteration 400: 1 [2026-03-26 00:18:21,654][__main__][INFO] - agents played in iteration 400 are Bob, Alice [2026-03-26 00:18:22,617][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:18:23,240][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:18:23,703][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:18:24,215][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:18:24,783][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:18:25,291][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:18:25,799][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:18:26,308][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:18:26,817][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:18:27,328][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:18:27,841][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:18:28,351][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:18:28,860][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:18:29,370][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:18:29,881][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:18:30,391][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:18:30,899][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:18:31,409][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:18:31,916][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:18:32,425][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:18:32,933][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:18:33,442][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:18:33,950][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:18:34,458][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:18:34,967][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:18:35,476][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:18:35,983][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:18:36,492][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:18:37,001][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:18:37,509][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:18:38,018][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:18:38,687][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:18:39,200][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:18:39,710][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:18:40,220][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:18:40,730][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:18:41,240][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:18:41,750][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:18:42,260][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:18:42,769][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:18:43,278][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:18:43,788][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:18:44,295][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:18:44,803][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:18:45,312][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:18:45,822][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:18:46,331][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:18:46,839][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:18:47,349][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:18:47,857][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:18:48,366][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:18:48,872][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:18:49,381][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:18:49,888][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:18:50,396][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:18:50,903][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:18:51,412][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:18:51,920][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:18:52,429][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:18:52,938][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:18:53,446][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:18:53,954][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:18:54,463][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:18:54,972][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:18:55,481][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:18:55,989][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:18:56,497][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:18:57,006][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:18:57,515][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:18:58,023][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:18:58,533][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:18:59,042][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:18:59,550][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:19:00,059][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:19:00,570][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:19:01,080][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:19:01,589][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:19:02,098][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:19:02,610][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:19:03,120][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:19:03,631][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:19:04,141][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:19:04,651][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:19:05,160][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:19:05,668][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:19:06,176][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:19:06,685][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:19:07,194][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:19:07,702][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:19:08,211][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:19:08,720][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:19:09,231][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:19:09,740][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:19:10,250][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:19:10,760][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:19:11,269][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:19:11,778][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:19:12,288][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:19:12,797][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:19:13,307][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:19:13,818][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:19:14,327][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:19:14,837][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:19:15,347][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:19:15,857][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:19:16,367][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:19:16,876][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:19:17,384][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:19:17,892][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:19:18,401][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:19:18,911][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:19:19,420][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:19:19,928][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:19:20,437][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:19:20,946][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:19:21,454][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:19:21,961][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:19:22,470][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:19:22,978][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:19:23,486][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:19:23,994][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:19:24,501][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:19:25,011][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:19:25,520][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:19:26,029][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:19:26,540][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:19:27,049][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:19:27,559][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:19:28,066][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:19:28,576][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21750 tokens. [2026-03-26 00:19:29,248][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:06 [2026-03-26 00:19:29,880][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:19:29,882][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:19:29,884][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:19:31,151][__main__][INFO] - Iteration 401 took 1m 17s (10.17% Gen, 88.19% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 43m 55s. Estimated total time: 64h 28m 13s. Time estimates for 10 more iterations: 12m 53s, 100 more iterations: 2h 8m 56s, 500 more iterations: 10h 44m 42s. [2026-03-26 00:19:31,155][__main__][INFO] - Starting iteration 401. [2026-03-26 00:19:31,555][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:19:31,556][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:19:39,427][__main__][INFO] - Number of regex retries in iteration 401: 0 [2026-03-26 00:19:39,428][__main__][INFO] - agents played in iteration 401 are Bob, Alice [2026-03-26 00:19:40,619][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:19:41,261][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:19:41,725][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:19:42,238][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:19:42,747][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:19:43,255][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:19:43,764][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:19:44,273][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:19:44,781][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:19:45,288][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:19:45,797][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:19:46,305][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:19:46,813][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:19:47,321][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:19:47,831][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:19:48,339][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:19:48,847][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:19:49,354][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:19:49,862][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:19:50,371][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:19:50,879][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:19:51,389][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:19:51,896][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:19:52,404][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:19:52,912][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:19:53,420][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:19:53,929][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:19:54,438][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:19:54,946][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:19:55,456][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:19:55,965][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:19:56,473][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:19:56,982][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:19:57,491][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:19:58,002][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:19:58,514][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:19:59,023][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:19:59,534][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:20:00,046][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:20:00,555][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:20:01,065][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:20:01,576][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:20:02,084][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:20:02,593][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:20:03,102][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:20:03,612][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:20:04,120][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:20:04,630][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:20:05,139][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:20:05,648][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:20:06,157][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:20:06,667][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:20:07,175][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:20:07,683][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:20:08,192][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:20:08,701][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:20:09,209][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:20:09,718][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:20:10,227][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:20:10,736][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:20:11,245][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:20:11,753][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:20:12,262][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:20:12,771][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:20:13,279][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:20:13,789][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:20:14,297][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:20:14,804][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:20:15,313][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:20:15,822][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:20:16,332][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:20:16,841][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:20:17,349][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:20:17,856][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:20:18,365][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:20:18,874][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:20:19,382][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:20:19,892][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:20:20,401][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:20:20,911][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:20:21,420][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:20:21,931][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:20:22,440][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:20:22,950][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:20:23,459][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:20:23,969][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:20:24,478][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:20:24,989][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:20:25,499][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:20:26,008][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:20:26,518][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:20:27,029][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:20:27,540][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:20:28,048][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:20:28,559][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:20:29,069][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:20:29,578][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:20:30,087][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:20:30,598][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:20:31,108][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:20:31,619][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:20:32,132][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:20:32,643][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:20:33,153][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:20:33,663][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:20:34,174][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:20:34,684][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:20:35,193][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:20:35,703][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:20:36,213][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:20:36,723][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:20:37,233][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:20:37,742][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:20:38,252][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:20:38,761][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:20:39,272][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:20:39,780][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:20:40,290][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:20:40,798][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:20:41,308][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:20:41,817][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:20:42,327][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:20:42,836][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:20:43,345][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:20:43,855][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:20:44,364][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:20:44,874][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:20:45,383][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:20:45,894][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:20:46,401][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21746 tokens. [2026-03-26 00:20:47,073][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 00:20:47,817][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:20:47,819][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:20:47,820][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:20:48,485][__main__][INFO] - Iteration 402 took 1m 16s (10.23% Gen, 88.90% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 20m 54s. Estimated total time: 64h 6m 29s. Time estimates for 10 more iterations: 12m 49s, 100 more iterations: 2h 8m 12s, 500 more iterations: 10h 41m 4s. [2026-03-26 00:20:48,487][__main__][INFO] - Starting iteration 402. [2026-03-26 00:20:48,889][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:20:48,890][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:20:53,706][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:20:56,716][__main__][INFO] - Number of regex retries in iteration 402: 1 [2026-03-26 00:20:56,717][__main__][INFO] - agents played in iteration 402 are Bob, Alice [2026-03-26 00:20:57,672][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:20:58,313][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:20:58,780][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:20:59,294][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:20:59,804][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:21:00,315][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:21:00,826][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:21:01,336][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:21:01,846][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:21:02,356][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:21:02,867][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:21:03,377][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:21:03,888][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:21:04,398][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:21:04,908][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:21:05,419][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:21:05,931][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:21:06,442][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:21:06,955][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:21:07,466][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:21:07,976][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:21:08,487][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:21:08,998][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:21:09,509][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:21:10,022][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:21:10,533][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:21:11,043][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:21:11,554][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:21:12,065][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:21:12,576][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:21:13,087][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:21:13,598][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:21:14,111][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:21:14,622][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:21:15,132][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:21:15,642][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:21:16,151][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:21:16,660][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:21:17,170][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:21:17,679][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:21:18,189][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:21:18,699][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:21:19,208][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:21:19,717][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:21:20,226][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:21:20,736][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:21:21,244][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:21:21,753][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:21:22,263][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:21:22,772][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:21:23,281][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:21:23,792][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:21:24,302][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:21:24,813][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:21:25,322][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:21:25,833][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:21:26,343][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:21:26,852][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:21:27,362][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:21:27,872][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:21:28,382][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:21:28,891][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:21:29,401][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:21:29,911][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:21:30,421][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:21:30,933][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:21:31,444][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:21:31,953][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:21:32,463][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:21:32,974][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:21:33,483][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:21:33,993][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:21:34,504][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:21:35,014][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:21:35,525][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:21:36,035][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:21:36,545][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:21:37,056][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:21:37,567][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:21:38,077][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:21:38,587][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:21:39,097][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:21:39,608][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:21:40,121][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:21:40,631][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:21:41,143][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:21:41,653][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:21:42,164][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:21:42,676][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:21:43,186][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:21:43,696][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:21:44,206][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:21:44,717][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:21:45,229][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:21:45,739][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:21:46,249][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:21:46,760][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:21:47,269][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:21:47,778][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:21:48,287][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:21:48,795][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:21:49,303][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:21:49,811][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:21:50,319][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:21:50,826][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:21:51,333][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:21:51,842][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:21:52,352][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:21:52,860][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:21:53,369][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:21:53,877][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:21:54,386][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:21:54,894][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:21:55,402][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:21:55,912][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:21:56,420][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:21:56,929][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:21:57,439][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:21:57,950][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:21:58,460][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:21:58,968][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:21:59,477][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:21:59,987][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:22:00,497][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:22:01,006][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:22:01,516][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:22:02,026][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:22:02,536][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:22:03,045][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:22:03,555][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21748 tokens. [2026-03-26 00:22:04,219][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.65%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:05 [2026-03-26 00:22:04,972][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:22:04,974][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:22:04,976][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:22:05,637][__main__][INFO] - Iteration 403 took 1m 16s (10.20% Gen, 88.94% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 55h 10m 34s. Estimated total time: 63h 57m 26s. Time estimates for 10 more iterations: 12m 47s, 100 more iterations: 2h 7m 54s, 500 more iterations: 10h 39m 34s. [2026-03-26 00:22:05,640][__main__][INFO] - Starting iteration 403. [2026-03-26 00:22:06,041][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:22:06,041][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:22:06,676][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:22:13,164][__main__][INFO] - Number of regex retries in iteration 403: 1 [2026-03-26 00:22:13,165][__main__][INFO] - agents played in iteration 403 are Bob, Alice [2026-03-26 00:22:14,152][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:22:15,073][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:22:15,537][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:22:16,049][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:22:16,556][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:22:17,064][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:22:17,571][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:22:18,080][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:22:18,587][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:22:19,095][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:22:19,606][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:22:20,115][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:22:20,624][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:22:21,133][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:22:21,642][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:22:22,151][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:22:22,660][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:22:23,170][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:22:23,678][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:22:24,184][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:22:24,692][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:22:25,199][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:22:25,706][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:22:26,214][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:22:26,721][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:22:27,229][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:22:27,738][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:22:28,247][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:22:28,757][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:22:29,266][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:22:29,775][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:22:30,285][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:22:30,793][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:22:31,302][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:22:31,811][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:22:32,317][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:22:32,825][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:22:33,333][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:22:33,841][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:22:34,350][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:22:34,857][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:22:35,364][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:22:35,872][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:22:36,379][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:22:36,888][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:22:37,396][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:22:37,903][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:22:38,414][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:22:38,922][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:22:39,431][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:22:39,941][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:22:40,450][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:22:40,959][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:22:41,468][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:22:41,976][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:22:42,486][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:22:42,994][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:22:43,502][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:22:44,012][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:22:44,520][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:22:45,028][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:22:45,536][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:22:46,045][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:22:46,553][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:22:47,062][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:22:47,571][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:22:48,078][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:22:48,586][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:22:49,093][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:22:49,600][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:22:50,107][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:22:50,614][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:22:51,121][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:22:51,629][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:22:52,137][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:22:52,646][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:22:53,155][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:22:53,664][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:22:54,173][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:22:54,681][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:22:55,189][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:22:55,699][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:22:56,206][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:22:56,713][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:22:57,218][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:22:57,725][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:22:58,232][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:22:58,739][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:22:59,246][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:22:59,754][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:23:00,263][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:23:00,772][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:23:01,281][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:23:01,792][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:23:02,301][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:23:02,810][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:23:03,319][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:23:03,830][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:23:04,337][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:23:04,845][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:23:05,352][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:23:05,859][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:23:06,367][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:23:06,874][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:23:07,381][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:23:07,890][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:23:08,398][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:23:08,905][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:23:09,414][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:23:09,921][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:23:10,430][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:23:10,939][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:23:11,450][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:23:11,960][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:23:12,469][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:23:12,978][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:23:13,488][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:23:13,997][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:23:14,506][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:23:15,015][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:23:15,524][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:23:16,034][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:23:16,542][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:23:17,051][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:23:17,560][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:23:18,067][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:23:18,576][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:23:19,084][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:23:19,592][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:23:20,101][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-26 00:23:20,760][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-26 00:23:21,507][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:23:21,509][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:23:21,511][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:23:22,161][__main__][INFO] - Iteration 404 took 1m 16s (9.36% Gen, 89.78% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 37m 54s. Estimated total time: 63h 26m 3s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 52s, 500 more iterations: 10h 34m 20s. [2026-03-26 00:23:22,163][__main__][INFO] - Starting iteration 404. [2026-03-26 00:23:22,568][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:23:22,569][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:23:23,183][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 0 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:23:29,270][__main__][INFO] - Number of regex retries in iteration 404: 1 [2026-03-26 00:23:29,271][__main__][INFO] - agents played in iteration 404 are Bob, Alice [2026-03-26 00:23:30,233][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:23:30,859][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:23:31,324][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:23:31,839][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:23:32,348][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:23:32,858][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:23:33,368][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:23:33,877][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:23:34,386][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:23:34,894][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:23:35,401][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:23:35,909][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:23:36,417][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:23:36,924][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:23:37,432][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:23:37,941][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:23:38,448][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:23:38,956][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:23:39,464][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:23:39,971][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:23:40,479][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:23:40,986][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:23:41,493][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:23:42,001][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:23:42,511][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:23:43,019][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:23:43,531][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:23:44,041][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:23:44,551][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:23:45,060][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:23:45,569][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:23:46,078][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:23:46,586][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:23:47,097][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:23:47,606][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:23:48,114][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:23:48,622][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:23:49,131][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:23:49,640][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:23:50,149][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:23:50,657][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:23:51,166][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:23:51,673][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:23:52,181][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:23:52,689][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:23:53,197][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:23:53,704][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:23:54,212][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:23:54,719][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:23:55,227][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:23:55,733][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:23:56,238][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:23:56,743][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:23:57,248][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:23:57,754][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:23:58,259][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:23:58,763][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:23:59,268][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:23:59,775][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:24:00,282][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:24:00,790][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:24:01,296][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:24:01,804][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:24:02,312][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:24:02,819][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:24:03,328][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:24:03,836][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:24:04,346][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:24:04,855][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:24:05,364][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:24:05,872][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:24:06,381][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:24:06,891][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:24:07,400][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:24:07,907][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:24:08,415][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:24:08,923][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:24:09,431][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:24:09,939][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:24:10,447][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:24:10,955][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:24:11,464][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:24:11,971][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:24:12,479][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:24:12,986][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:24:13,494][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:24:14,002][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:24:14,510][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:24:15,018][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:24:15,526][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:24:16,035][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:24:16,545][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:24:17,054][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:24:17,563][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:24:18,073][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:24:18,582][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:24:19,092][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:24:19,601][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:24:20,110][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:24:20,618][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:24:21,127][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:24:21,636][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:24:22,144][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:24:22,652][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:24:23,161][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:24:23,669][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:24:24,177][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:24:24,685][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:24:25,193][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:24:25,700][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:24:26,209][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:24:26,718][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:24:27,225][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:24:27,733][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:24:28,239][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:24:28,744][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:24:29,249][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:24:29,753][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:24:30,258][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:24:30,762][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:24:31,267][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:24:31,772][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:24:32,280][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:24:32,789][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:24:33,297][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:24:33,805][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:24:34,313][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:24:34,821][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:24:35,330][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:24:35,840][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 00:24:36,496][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-26 00:24:37,243][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:24:37,246][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:24:37,247][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:24:37,903][__main__][INFO] - Iteration 405 took 1m 15s (8.90% Gen, 90.23% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 53h 57m 22s. Estimated total time: 62h 46m 46s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 33s, 500 more iterations: 10h 27m 47s. [2026-03-26 00:24:37,905][__main__][INFO] - Starting iteration 405. [2026-03-26 00:24:38,305][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:24:38,306][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:24:45,005][__main__][INFO] - Number of regex retries in iteration 405: 0 [2026-03-26 00:24:45,006][__main__][INFO] - agents played in iteration 405 are Bob, Alice [2026-03-26 00:24:45,968][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:24:46,595][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:24:47,064][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:24:47,579][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:24:48,087][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:24:48,597][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:24:49,106][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:24:49,615][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:24:50,125][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:24:50,633][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:24:51,142][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:24:51,651][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:24:52,158][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:24:52,664][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:24:53,172][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:24:53,679][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:24:54,186][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:24:54,693][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:24:55,202][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:24:55,710][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:24:56,218][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:24:56,727][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:24:57,236][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:24:57,744][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:24:58,253][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:24:58,761][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:24:59,272][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:24:59,781][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:25:00,290][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:25:00,799][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:25:01,308][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:25:01,818][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:25:02,328][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:25:02,838][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:25:03,346][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:25:03,855][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:25:04,363][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:25:04,872][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:25:05,381][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:25:05,889][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:25:06,397][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:25:06,906][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:25:07,415][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:25:07,923][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:25:08,431][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:25:08,940][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:25:09,449][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:25:09,957][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:25:10,466][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:25:10,974][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:25:11,482][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:25:11,992][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:25:12,499][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:25:13,007][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:25:13,514][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:25:14,022][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:25:14,531][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:25:15,039][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:25:15,547][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:25:16,055][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:25:16,562][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:25:17,070][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:25:17,578][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:25:18,085][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:25:18,593][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:25:19,103][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:25:19,612][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:25:20,120][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:25:20,630][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:25:21,140][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:25:21,651][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:25:22,161][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:25:22,670][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:25:23,178][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:25:23,686][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:25:24,193][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:25:24,701][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:25:25,209][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:25:25,716][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:25:26,223][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:25:26,730][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:25:27,238][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:25:27,746][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:25:28,254][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:25:28,763][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:25:29,272][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:25:29,780][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:25:30,288][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:25:30,796][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:25:31,304][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:25:31,813][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:25:32,321][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:25:32,833][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:25:33,342][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:25:33,852][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:25:34,361][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:25:34,870][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:25:35,379][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:25:35,887][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:25:36,395][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:25:36,901][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:25:37,410][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:25:37,917][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:25:38,425][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:25:38,933][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:25:39,442][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:25:39,951][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:25:40,460][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:25:40,970][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:25:41,479][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:25:41,988][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:25:42,495][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:25:43,004][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:25:43,512][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:25:44,020][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:25:44,529][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:25:45,037][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:25:45,544][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:25:46,051][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:25:46,558][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:25:47,066][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:25:47,573][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:25:48,083][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:25:48,592][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:25:49,101][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:25:49,610][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:25:50,118][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:25:50,627][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:25:51,135][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:25:51,644][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-26 00:25:52,304][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-26 00:25:53,046][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:25:53,048][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:25:53,050][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:25:53,704][__main__][INFO] - Iteration 406 took 1m 15s (8.89% Gen, 90.24% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 59m 19s. Estimated total time: 62h 49m 59s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 39s, 500 more iterations: 10h 28m 19s. [2026-03-26 00:25:53,706][__main__][INFO] - Starting iteration 406. [2026-03-26 00:25:54,107][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:25:54,107][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:26:01,086][__main__][INFO] - Number of regex retries in iteration 406: 0 [2026-03-26 00:26:01,088][__main__][INFO] - agents played in iteration 406 are Bob, Alice [2026-03-26 00:26:02,330][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:26:02,953][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:26:03,419][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:26:03,933][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:26:04,444][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:26:04,953][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:26:05,462][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:26:05,971][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:26:06,480][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:26:06,988][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:26:07,496][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:26:08,003][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:26:08,511][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:26:09,019][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:26:09,528][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:26:10,037][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:26:10,545][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:26:11,054][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:26:11,561][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:26:12,069][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:26:12,576][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:26:13,084][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:26:13,592][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:26:14,100][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:26:14,607][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:26:15,115][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:26:15,626][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:26:16,136][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:26:16,646][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:26:17,156][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:26:17,667][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:26:18,177][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:26:18,685][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:26:19,196][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:26:19,705][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:26:20,214][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:26:20,722][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:26:21,232][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:26:21,740][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:26:22,249][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:26:22,758][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:26:23,266][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:26:23,775][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:26:24,283][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:26:24,792][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:26:25,301][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:26:25,810][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:26:26,318][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:26:26,827][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:26:27,336][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:26:27,845][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:26:28,353][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:26:28,862][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:26:29,370][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:26:29,879][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:26:30,388][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:26:30,897][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:26:31,405][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:26:31,914][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:26:32,422][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:26:32,929][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:26:33,439][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:26:33,947][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:26:34,455][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:26:34,963][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:26:35,471][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:26:35,979][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:26:36,487][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:26:36,997][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:26:37,505][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:26:38,013][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:26:38,522][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:26:39,030][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:26:39,537][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:26:40,047][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:26:40,554][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:26:41,063][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:26:41,572][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:26:42,080][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:26:42,588][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:26:43,097][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:26:43,604][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:26:44,113][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:26:44,620][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:26:45,126][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:26:45,634][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:26:46,140][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:26:46,648][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:26:47,155][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:26:47,662][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:26:48,173][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:26:48,683][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:26:49,194][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:26:49,703][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:26:50,213][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:26:50,721][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:26:51,232][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:26:51,741][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:26:52,250][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:26:52,760][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:26:53,266][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:26:53,775][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:26:54,285][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:26:54,793][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:26:55,300][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:26:55,810][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:26:56,319][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:26:56,828][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:26:57,337][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:26:57,846][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:26:58,355][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:26:58,864][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:26:59,373][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:26:59,882][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:27:00,391][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:27:00,898][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:27:01,407][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:27:01,915][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:27:02,423][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:27:02,933][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:27:03,442][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:27:03,951][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:27:04,460][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:27:04,967][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:27:05,475][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:27:05,983][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:27:06,491][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:27:07,000][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:27:07,508][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:27:08,017][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 00:27:08,666][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 00:27:09,404][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:27:09,406][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:27:09,408][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:27:10,213][__main__][INFO] - Iteration 407 took 1m 16s (9.17% Gen, 89.77% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 33m 23s. Estimated total time: 63h 25m 20s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 50s, 500 more iterations: 10h 34m 13s. [2026-03-26 00:27:10,215][__main__][INFO] - Starting iteration 407. [2026-03-26 00:27:10,617][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:27:10,618][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:27:13,216][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:27:18,235][__main__][INFO] - Number of regex retries in iteration 407: 1 [2026-03-26 00:27:18,236][__main__][INFO] - agents played in iteration 407 are Bob, Alice [2026-03-26 00:27:19,405][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:27:20,025][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:27:20,488][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:27:21,002][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:27:21,511][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:27:22,019][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:27:22,528][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:27:23,036][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:27:23,544][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:27:24,052][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:27:24,561][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:27:25,070][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:27:25,578][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:27:26,085][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:27:26,593][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:27:27,101][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:27:27,609][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:27:28,117][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:27:28,621][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:27:29,127][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:27:29,637][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:27:30,144][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:27:30,651][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:27:31,160][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:27:31,668][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:27:32,176][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:27:32,684][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:27:33,192][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:27:33,700][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:27:34,208][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:27:34,717][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:27:35,225][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:27:35,732][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:27:36,241][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:27:36,750][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:27:37,257][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:27:37,765][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:27:38,274][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:27:38,781][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:27:39,288][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:27:39,794][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:27:40,302][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:27:40,811][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:27:41,321][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:27:41,829][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:27:42,338][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:27:42,845][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:27:43,354][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:27:43,862][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:27:44,368][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:27:44,878][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:27:45,388][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:27:45,897][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:27:46,406][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:27:46,915][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:27:47,424][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:27:47,934][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:27:48,443][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:27:48,952][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:27:49,460][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:27:49,968][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:27:50,476][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:27:50,984][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:27:51,494][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:27:52,001][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:27:52,511][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:27:53,020][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:27:53,529][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:27:54,038][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:27:54,546][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:27:55,055][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:27:55,562][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:27:56,071][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:27:56,579][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:27:57,087][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:27:57,596][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:27:58,105][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:27:58,614][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:27:59,123][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:27:59,632][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:28:00,141][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:28:00,649][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:28:01,157][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:28:01,664][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:28:02,172][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:28:02,680][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:28:03,188][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:28:03,696][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:28:04,203][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:28:04,712][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:28:05,220][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:28:05,730][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:28:06,239][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:28:06,748][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:28:07,257][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:28:07,765][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:28:08,273][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:28:08,781][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:28:09,288][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:28:09,794][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:28:10,302][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:28:10,809][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:28:11,317][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:28:11,825][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:28:12,333][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:28:12,841][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:28:13,349][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:28:13,857][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:28:14,365][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:28:14,872][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:28:15,379][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:28:15,887][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:28:16,395][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:28:16,902][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:28:17,411][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:28:17,920][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:28:18,429][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:28:18,939][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:28:19,450][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:28:19,960][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:28:20,469][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:28:20,978][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:28:21,487][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:28:21,995][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:28:22,503][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:28:23,011][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:28:23,520][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:28:24,029][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:28:24,537][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:28:25,047][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21716 tokens. [2026-03-26 00:28:25,709][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-26 00:28:26,449][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:28:26,452][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:28:26,453][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:28:27,107][__main__][INFO] - Iteration 408 took 1m 16s (9.96% Gen, 89.18% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 51m 18s. Estimated total time: 63h 44m 32s. Time estimates for 10 more iterations: 12m 44s, 100 more iterations: 2h 7m 29s, 500 more iterations: 10h 37m 25s. [2026-03-26 00:28:27,111][__main__][INFO] - Starting iteration 408. [2026-03-26 00:28:27,513][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:28:27,514][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:28:34,626][__main__][INFO] - Number of regex retries in iteration 408: 0 [2026-03-26 00:28:34,627][__main__][INFO] - agents played in iteration 408 are Bob, Alice [2026-03-26 00:28:35,593][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:28:36,227][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:28:36,692][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:28:37,205][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:28:37,714][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:28:38,223][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:28:38,732][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:28:39,241][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:28:39,751][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:28:40,261][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:28:40,769][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:28:41,278][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:28:41,787][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:28:42,296][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:28:42,804][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:28:43,313][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:28:43,821][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:28:44,330][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:28:44,839][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:28:45,348][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:28:45,857][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:28:46,366][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:28:46,875][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:28:47,383][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:28:47,892][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:28:48,401][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:28:48,913][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:28:49,424][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:28:49,934][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:28:50,444][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:28:50,956][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:28:51,466][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:28:51,976][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:28:52,487][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:28:52,996][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:28:53,506][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:28:54,015][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:28:54,525][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:28:55,034][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:28:55,544][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:28:56,053][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:28:56,563][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:28:57,071][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:28:57,580][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:28:58,091][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:28:58,601][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:28:59,109][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:28:59,618][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:29:00,127][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:29:00,636][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:29:01,146][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:29:01,656][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:29:02,164][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:29:02,674][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:29:03,182][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:29:03,692][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:29:04,201][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:29:04,710][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:29:05,218][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:29:05,727][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:29:06,236][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:29:06,744][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:29:07,252][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:29:07,760][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:29:08,268][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:29:08,775][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:29:09,284][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:29:09,792][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:29:10,301][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:29:10,810][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:29:11,319][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:29:11,829][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:29:12,338][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:29:12,846][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:29:13,355][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:29:13,863][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:29:14,371][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:29:14,879][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:29:15,387][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:29:15,896][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:29:16,403][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:29:16,911][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:29:17,420][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:29:17,930][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:29:18,438][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:29:18,947][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:29:19,456][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:29:19,964][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:29:20,473][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:29:20,981][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:29:21,492][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:29:22,002][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:29:22,512][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:29:23,022][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:29:23,533][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:29:24,042][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:29:24,554][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:29:25,064][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:29:25,573][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:29:26,082][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:29:26,591][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:29:27,101][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:29:27,611][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:29:28,120][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:29:28,630][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:29:29,141][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:29:29,649][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:29:30,158][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:29:30,667][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:29:31,175][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:29:31,683][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:29:32,192][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:29:32,700][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:29:33,209][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:29:33,718][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:29:34,226][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:29:34,735][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:29:35,243][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:29:35,753][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:29:36,263][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:29:36,772][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:29:37,280][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:29:37,790][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:29:38,298][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:29:38,806][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:29:39,314][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:29:39,823][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:29:40,331][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:29:40,840][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:29:41,349][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 00:29:42,012][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-26 00:29:42,756][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:29:42,758][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:29:42,760][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:29:43,416][__main__][INFO] - Iteration 409 took 1m 15s (9.37% Gen, 89.76% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 20m 43s. Estimated total time: 63h 15m 13s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 30s, 500 more iterations: 10h 32m 32s. [2026-03-26 00:29:43,419][__main__][INFO] - Starting iteration 409. [2026-03-26 00:29:43,819][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:29:43,820][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:29:51,054][__main__][INFO] - Number of regex retries in iteration 409: 0 [2026-03-26 00:29:51,055][__main__][INFO] - agents played in iteration 409 are Bob, Alice [2026-03-26 00:29:52,006][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:29:52,630][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:29:53,095][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:29:53,611][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:29:54,121][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:29:54,632][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:29:55,142][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:29:55,651][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:29:56,161][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:29:56,669][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:29:57,178][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:29:57,685][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:29:58,193][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:29:58,701][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:29:59,212][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:29:59,720][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:30:00,227][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:30:00,736][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:30:01,245][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:30:01,753][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:30:02,261][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:30:02,771][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:30:03,280][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:30:03,788][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:30:04,296][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:30:04,804][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:30:05,313][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:30:05,822][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:30:06,332][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:30:06,841][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:30:07,349][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:30:07,858][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:30:08,366][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:30:08,875][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:30:09,386][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:30:09,896][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:30:10,406][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:30:10,917][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:30:11,426][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:30:11,937][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:30:12,446][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:30:12,957][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:30:13,465][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:30:13,974][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:30:14,482][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:30:14,991][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:30:15,499][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:30:16,007][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:30:16,516][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:30:17,024][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:30:17,533][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:30:18,042][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:30:18,551][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:30:19,058][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:30:19,566][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:30:20,074][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:30:20,582][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:30:21,090][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:30:21,599][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:30:22,109][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:30:22,617][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:30:23,125][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:30:23,635][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:30:24,144][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:30:24,653][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:30:25,161][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:30:25,671][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:30:26,181][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:30:26,689][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:30:27,199][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:30:27,708][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:30:28,217][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:30:28,727][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:30:29,237][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:30:29,746][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:30:30,253][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:30:30,761][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:30:31,270][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:30:31,778][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:30:32,288][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:30:32,796][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:30:33,303][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:30:33,811][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:30:34,320][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:30:34,831][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:30:35,340][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:30:35,849][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:30:36,357][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:30:36,865][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:30:37,374][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:30:37,882][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:30:38,391][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:30:38,900][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:30:39,409][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:30:39,916][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:30:40,425][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:30:40,933][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:30:41,442][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:30:41,951][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:30:42,460][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:30:42,969][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:30:43,480][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:30:43,990][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:30:44,500][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:30:45,010][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:30:45,520][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:30:46,030][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:30:46,539][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:30:47,047][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:30:47,556][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:30:48,064][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:30:48,573][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:30:49,081][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:30:49,589][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:30:50,097][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:30:50,605][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:30:51,113][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:30:51,620][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:30:52,129][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:30:52,638][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:30:53,145][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:30:53,653][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:30:54,161][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:30:54,669][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:30:55,177][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:30:55,685][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:30:56,193][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:30:56,701][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:30:57,209][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:30:57,717][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21710 tokens. [2026-03-26 00:30:58,371][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:05 [2026-03-26 00:30:59,125][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:30:59,127][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:30:59,129][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:30:59,787][__main__][INFO] - Iteration 410 took 1m 15s (9.52% Gen, 89.61% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 22m 37s. Estimated total time: 63h 18m 24s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 36s, 500 more iterations: 10h 33m 4s. [2026-03-26 00:30:59,789][__main__][INFO] - Starting iteration 410. [2026-03-26 00:31:00,191][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:31:00,192][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:31:06,970][__main__][INFO] - Number of regex retries in iteration 410: 0 [2026-03-26 00:31:06,972][__main__][INFO] - agents played in iteration 410 are Bob, Alice [2026-03-26 00:31:08,230][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:31:08,859][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:31:09,324][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:31:09,837][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:31:10,346][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:31:10,854][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:31:11,364][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:31:11,873][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:31:12,382][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:31:12,891][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:31:13,399][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:31:13,907][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:31:14,415][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:31:14,923][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:31:15,434][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:31:15,945][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:31:16,453][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:31:16,962][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:31:17,474][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:31:17,982][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:31:18,493][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:31:19,002][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:31:19,512][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:31:20,022][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:31:20,532][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:31:21,042][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:31:21,552][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:31:22,061][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:31:22,571][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:31:23,080][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:31:23,585][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:31:24,094][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:31:24,603][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:31:25,113][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:31:25,622][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:31:26,131][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:31:26,640][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:31:27,150][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:31:27,658][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:31:28,167][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:31:28,676][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:31:29,185][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:31:29,693][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:31:30,202][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:31:30,712][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:31:31,222][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:31:31,733][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:31:32,242][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:31:32,751][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:31:33,260][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:31:33,770][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:31:34,281][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:31:34,791][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:31:35,299][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:31:35,810][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:31:36,319][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:31:36,829][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:31:37,340][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:31:37,850][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:31:38,359][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:31:38,868][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:31:39,377][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:31:39,886][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:31:40,394][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:31:40,902][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:31:41,412][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:31:41,921][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:31:42,431][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:31:42,940][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:31:43,451][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:31:43,961][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:31:44,469][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:31:44,979][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:31:45,489][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:31:45,997][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:31:46,506][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:31:47,015][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:31:47,524][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:31:48,033][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:31:48,543][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:31:49,052][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:31:49,561][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:31:50,071][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:31:50,580][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:31:51,088][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:31:51,597][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:31:52,105][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:31:52,614][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:31:53,123][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:31:53,633][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:31:54,143][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:31:54,651][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:31:55,159][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:31:55,667][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:31:56,175][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:31:56,683][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:31:57,193][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:31:57,702][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:31:58,212][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:31:58,720][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:31:59,230][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:31:59,739][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:32:00,248][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:32:00,757][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:32:01,266][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:32:01,775][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:32:02,284][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:32:02,793][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:32:03,301][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:32:03,811][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:32:04,320][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:32:04,829][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:32:05,338][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:32:05,847][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:32:06,355][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:32:06,863][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:32:07,372][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:32:07,881][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:32:08,390][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:32:08,897][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:32:09,406][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:32:09,915][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:32:10,423][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:32:10,932][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:32:11,439][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:32:11,946][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:32:12,455][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:32:12,963][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:32:13,473][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:32:13,982][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21727 tokens. [2026-03-26 00:32:14,638][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.23%, ΔTime: 00:01:05 [2026-03-26 00:32:15,391][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:32:15,394][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:32:15,395][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:32:16,074][__main__][INFO] - Iteration 411 took 1m 15s (8.93% Gen, 90.17% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 17m 7s. Estimated total time: 63h 14m 10s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 28s, 500 more iterations: 10h 32m 21s. [2026-03-26 00:32:16,076][__main__][INFO] - Starting iteration 411. [2026-03-26 00:32:16,478][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:32:16,479][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:32:22,501][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:32:23,581][__main__][INFO] - Number of regex retries in iteration 411: 1 [2026-03-26 00:32:23,582][__main__][INFO] - agents played in iteration 411 are Bob, Alice [2026-03-26 00:32:24,543][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:32:25,174][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:32:25,639][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:32:26,154][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:32:26,663][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:32:27,173][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:32:27,681][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:32:28,189][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:32:28,697][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:32:29,206][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:32:29,715][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:32:30,223][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:32:30,733][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:32:31,242][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:32:31,752][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:32:32,261][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:32:32,768][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:32:33,278][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:32:33,787][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:32:34,296][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:32:34,805][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:32:35,314][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:32:35,823][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:32:36,333][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:32:36,842][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:32:37,352][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:32:37,863][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:32:38,373][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:32:38,882][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:32:39,391][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:32:39,900][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:32:40,412][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:32:40,921][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:32:41,430][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:32:41,938][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:32:42,446][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:32:42,954][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:32:43,462][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:32:43,970][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:32:44,479][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:32:44,986][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:32:45,494][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:32:46,002][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:32:46,512][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:32:47,021][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:32:47,533][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:32:48,043][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:32:48,553][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:32:49,063][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:32:49,573][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:32:50,083][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:32:50,592][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:32:51,101][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:32:51,614][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:32:52,124][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:32:52,634][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:32:53,144][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:32:53,654][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:32:54,164][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:32:54,674][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:32:55,183][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:32:55,692][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:32:56,202][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:32:56,711][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:32:57,220][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:32:57,730][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:32:58,240][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:32:58,751][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:32:59,262][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:32:59,770][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:33:00,280][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:33:00,790][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:33:01,300][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:33:01,811][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:33:02,320][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:33:02,831][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:33:03,341][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:33:03,850][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:33:04,360][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:33:04,869][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:33:05,378][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:33:05,888][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:33:06,398][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:33:06,907][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:33:07,416][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:33:07,926][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:33:08,437][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:33:08,946][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:33:09,457][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:33:09,967][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:33:10,477][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:33:10,987][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:33:11,496][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:33:12,007][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:33:12,517][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:33:13,027][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:33:13,537][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:33:14,047][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:33:14,556][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:33:15,065][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:33:15,574][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:33:16,084][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:33:16,593][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:33:17,101][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:33:17,609][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:33:18,118][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:33:18,629][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:33:19,139][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:33:19,648][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:33:20,158][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:33:20,669][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:33:21,178][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:33:21,689][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:33:22,199][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:33:22,710][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:33:23,221][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:33:23,731][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:33:24,241][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:33:24,750][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:33:25,258][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:33:25,766][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:33:26,275][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:33:26,784][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:33:27,292][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:33:27,801][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:33:28,310][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:33:28,819][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:33:29,327][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:33:29,836][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:33:30,345][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 00:33:31,004][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.23%, ΔTime: 00:01:05 [2026-03-26 00:33:31,753][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:33:31,756][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:33:31,757][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:33:32,422][__main__][INFO] - Iteration 412 took 1m 15s (9.35% Gen, 89.77% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 18m 55s. Estimated total time: 63h 17m 14s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 34s, 500 more iterations: 10h 32m 52s. [2026-03-26 00:33:32,424][__main__][INFO] - Starting iteration 412. [2026-03-26 00:33:32,826][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:33:32,827][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:33:40,061][__main__][INFO] - Number of regex retries in iteration 412: 0 [2026-03-26 00:33:40,062][__main__][INFO] - agents played in iteration 412 are Bob, Alice [2026-03-26 00:33:41,030][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:33:41,665][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:33:42,131][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:33:42,646][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:33:43,156][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:33:43,666][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:33:44,176][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:33:44,688][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:33:45,198][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:33:45,708][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:33:46,217][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:33:46,726][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:33:47,236][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:33:47,744][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:33:48,253][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:33:48,762][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:33:49,270][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:33:49,778][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:33:50,288][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:33:50,798][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:33:51,307][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:33:51,817][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:33:52,327][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:33:52,836][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:33:53,346][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:33:53,855][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:33:54,364][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:33:54,873][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:33:55,381][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:33:55,891][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:33:56,400][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:33:56,910][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:33:57,419][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:33:57,929][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:33:58,441][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:33:58,953][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:33:59,464][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:33:59,975][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:34:00,484][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:34:00,994][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:34:01,504][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:34:02,015][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:34:02,523][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:34:03,033][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:34:03,542][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:34:04,051][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:34:04,561][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:34:05,069][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:34:05,578][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:34:06,086][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:34:06,595][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:34:07,104][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:34:07,614][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:34:08,123][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:34:08,633][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:34:09,142][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:34:09,651][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:34:10,160][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:34:10,669][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:34:11,178][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:34:11,688][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:34:12,199][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:34:12,707][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:34:13,216][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:34:13,726][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:34:14,236][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:34:14,746][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:34:15,256][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:34:15,766][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:34:16,275][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:34:16,786][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:34:17,297][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:34:17,806][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:34:18,316][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:34:18,824][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:34:19,333][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:34:19,841][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:34:20,350][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:34:20,858][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:34:21,367][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:34:21,875][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:34:22,382][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:34:22,892][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:34:23,401][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:34:23,911][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:34:24,420][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:34:24,931][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:34:25,441][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:34:25,950][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:34:26,459][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:34:26,968][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:34:27,476][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:34:27,985][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:34:28,495][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:34:29,004][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:34:29,513][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:34:30,022][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:34:30,532][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:34:31,042][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:34:31,553][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:34:32,064][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:34:32,575][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:34:33,087][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:34:33,597][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:34:34,109][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:34:34,621][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:34:35,133][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:34:35,643][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:34:36,152][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:34:36,661][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:34:37,172][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:34:37,682][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:34:38,191][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:34:38,699][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:34:39,210][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:34:39,720][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:34:40,229][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:34:40,739][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:34:41,249][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:34:41,758][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:34:42,267][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:34:42,777][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:34:43,287][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:34:43,797][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:34:44,307][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:34:44,817][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:34:45,327][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:34:45,837][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:34:46,349][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:34:46,859][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 00:34:47,522][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:05 [2026-03-26 00:34:48,275][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:34:48,278][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:34:48,279][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:34:49,194][__main__][INFO] - Iteration 413 took 1m 16s (9.47% Gen, 89.33% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 38m 50s. Estimated total time: 63h 38m 26s. Time estimates for 10 more iterations: 12m 43s, 100 more iterations: 2h 7m 16s, 500 more iterations: 10h 36m 24s. [2026-03-26 00:34:49,196][__main__][INFO] - Starting iteration 413. [2026-03-26 00:34:49,597][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:34:49,598][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:34:50,232][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:34:54,071][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:34:57,144][__main__][INFO] - Number of regex retries in iteration 413: 2 [2026-03-26 00:34:57,145][__main__][INFO] - agents played in iteration 413 are Bob, Alice [2026-03-26 00:34:58,105][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:34:58,737][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:34:59,203][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:34:59,716][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:35:00,225][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:35:00,735][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:35:01,243][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:35:01,753][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:35:02,262][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:35:02,770][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:35:03,276][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:35:03,786][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:35:04,294][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:35:04,801][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:35:05,310][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:35:05,820][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:35:06,330][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:35:06,838][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:35:07,351][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:35:07,861][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:35:08,370][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:35:08,880][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:35:09,390][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:35:09,899][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:35:10,410][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:35:10,918][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:35:11,427][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:35:11,935][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:35:12,444][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:35:12,954][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:35:13,462][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:35:13,971][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:35:14,479][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:35:14,988][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:35:15,496][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:35:16,003][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:35:16,514][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:35:17,023][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:35:17,531][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:35:18,039][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:35:18,547][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:35:19,055][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:35:19,564][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:35:20,072][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:35:20,580][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:35:21,089][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:35:21,597][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:35:22,106][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:35:22,614][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:35:23,122][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:35:23,631][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:35:24,143][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:35:24,654][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:35:25,163][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:35:25,676][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:35:26,186][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:35:26,695][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:35:27,212][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:35:27,720][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:35:28,229][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:35:28,739][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:35:29,249][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:35:29,758][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:35:30,266][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:35:30,775][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:35:31,283][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:35:31,791][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:35:32,299][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:35:32,806][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:35:33,316][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:35:33,824][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:35:34,333][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:35:34,841][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:35:35,351][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:35:35,860][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:35:36,368][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:35:36,878][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:35:37,387][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:35:37,894][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:35:38,402][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:35:38,913][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:35:39,422][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:35:39,931][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:35:40,440][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:35:40,950][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:35:41,459][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:35:41,968][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:35:42,477][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:35:42,986][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:35:43,494][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:35:44,001][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:35:44,511][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:35:45,019][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:35:45,527][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:35:46,034][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:35:46,542][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:35:47,050][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:35:47,558][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:35:48,065][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:35:48,573][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:35:49,081][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:35:49,588][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:35:50,096][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:35:50,604][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:35:51,112][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:35:51,621][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:35:52,131][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:35:52,640][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:35:53,149][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:35:53,657][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:35:54,165][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:35:54,672][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:35:55,180][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:35:55,688][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:35:56,197][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:35:56,706][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:35:57,215][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:35:57,726][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:35:58,236][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:35:58,747][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:35:59,256][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:35:59,766][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:36:00,274][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:36:00,782][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:36:01,290][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:36:01,799][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:36:02,308][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:36:02,816][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:36:03,323][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:36:03,834][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21723 tokens. [2026-03-26 00:36:04,512][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 00:36:05,254][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:36:05,256][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:36:05,258][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:36:05,960][__main__][INFO] - Iteration 414 took 1m 16s (9.88% Gen, 89.19% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 37m 20s. Estimated total time: 63h 38m 12s. Time estimates for 10 more iterations: 12m 43s, 100 more iterations: 2h 7m 16s, 500 more iterations: 10h 36m 22s. [2026-03-26 00:36:05,962][__main__][INFO] - Starting iteration 414. [2026-03-26 00:36:06,367][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:36:06,367][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:36:13,784][__main__][INFO] - Number of regex retries in iteration 414: 0 [2026-03-26 00:36:13,785][__main__][INFO] - agents played in iteration 414 are Bob, Alice [2026-03-26 00:36:14,744][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:36:15,372][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:36:15,839][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:36:16,352][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:36:16,860][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:36:17,369][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:36:17,877][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:36:18,385][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:36:18,894][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:36:19,403][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:36:19,914][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:36:20,423][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:36:20,933][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:36:21,443][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:36:21,952][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:36:22,461][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:36:22,970][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:36:23,480][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:36:23,989][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:36:24,497][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:36:25,005][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:36:25,514][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:36:26,022][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:36:26,532][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:36:27,040][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:36:27,549][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:36:28,057][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:36:28,567][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:36:29,074][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:36:29,580][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:36:30,086][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:36:30,595][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:36:31,104][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:36:31,612][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:36:32,123][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:36:32,631][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:36:33,140][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:36:33,651][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:36:34,160][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:36:34,668][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:36:35,177][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:36:35,685][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:36:36,193][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:36:36,700][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:36:37,208][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:36:37,717][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:36:38,226][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:36:38,734][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:36:39,242][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:36:39,751][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:36:40,259][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:36:40,766][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:36:41,274][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:36:41,781][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:36:42,289][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:36:42,796][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:36:43,303][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:36:43,811][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:36:44,319][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:36:44,827][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:36:45,335][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:36:45,843][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:36:46,352][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:36:46,860][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:36:47,369][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:36:47,878][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:36:48,386][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:36:48,892][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:36:49,401][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:36:49,909][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:36:50,418][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:36:50,925][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:36:51,435][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:36:51,943][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:36:52,452][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:36:52,961][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:36:53,470][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:36:53,979][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:36:54,485][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:36:54,993][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:36:55,502][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:36:56,013][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:36:56,521][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:36:57,032][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:36:57,542][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:36:58,050][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:36:58,557][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:36:59,066][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:36:59,573][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:37:00,081][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:37:00,590][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:37:01,098][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:37:01,606][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:37:02,115][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:37:02,623][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:37:03,132][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:37:03,641][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:37:04,149][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:37:04,658][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:37:05,167][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:37:05,675][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:37:06,183][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:37:06,694][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:37:07,204][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:37:07,714][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:37:08,224][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:37:08,732][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:37:09,240][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:37:09,748][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:37:10,255][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:37:10,763][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:37:11,271][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:37:11,779][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:37:12,287][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:37:12,795][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:37:13,302][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:37:13,810][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:37:14,318][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:37:14,825][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:37:15,332][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:37:15,840][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:37:16,350][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:37:16,858][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:37:17,366][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:37:17,875][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:37:18,384][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:37:18,892][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:37:19,400][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:37:19,909][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:37:20,419][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-26 00:37:21,090][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-26 00:37:21,842][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:37:21,844][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:37:21,846][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:37:22,510][__main__][INFO] - Iteration 415 took 1m 16s (9.74% Gen, 89.38% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 25m 3s. Estimated total time: 63h 27m 12s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 54s, 500 more iterations: 10h 34m 32s. [2026-03-26 00:37:22,512][__main__][INFO] - Starting iteration 415. [2026-03-26 00:37:22,928][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:37:22,929][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:37:30,553][__main__][INFO] - Number of regex retries in iteration 415: 0 [2026-03-26 00:37:30,554][__main__][INFO] - agents played in iteration 415 are Bob, Alice [2026-03-26 00:37:31,697][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:37:32,320][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:37:32,784][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:37:33,299][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:37:33,808][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:37:34,317][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:37:34,825][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:37:35,334][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:37:35,843][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:37:36,351][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:37:36,860][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:37:37,368][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:37:37,877][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:37:38,383][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:37:38,894][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:37:39,401][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:37:39,908][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:37:40,415][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:37:40,926][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:37:41,435][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:37:41,943][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:37:42,453][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:37:42,960][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:37:43,469][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:37:43,978][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:37:44,486][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:37:44,994][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:37:45,502][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:37:46,010][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:37:46,518][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:37:47,025][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:37:47,534][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:37:48,042][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:37:48,550][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:37:49,060][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:37:49,568][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:37:50,076][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:37:50,585][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:37:51,095][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:37:51,604][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:37:52,113][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:37:52,622][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:37:53,131][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:37:53,638][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:37:54,145][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:37:54,653][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:37:55,161][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:37:55,669][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:37:56,177][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:37:56,684][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:37:57,193][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:37:57,701][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:37:58,212][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:37:58,721][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:37:59,229][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:37:59,738][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:38:00,247][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:38:00,756][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:38:01,264][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:38:01,772][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:38:02,280][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:38:02,788][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:38:03,296][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:38:03,803][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:38:04,312][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:38:04,820][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:38:05,328][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:38:05,837][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:38:06,346][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:38:06,854][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:38:07,362][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:38:07,871][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:38:08,380][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:38:08,889][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:38:09,397][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:38:09,905][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:38:10,414][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:38:10,923][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:38:11,432][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:38:11,942][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:38:12,450][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:38:12,959][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:38:13,467][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:38:13,977][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:38:14,485][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:38:14,994][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:38:15,502][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:38:16,012][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:38:16,521][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:38:17,032][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:38:17,541][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:38:18,049][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:38:18,557][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:38:19,065][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:38:19,573][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:38:20,080][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:38:20,587][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:38:21,095][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:38:21,603][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:38:22,111][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:38:22,621][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:38:23,132][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:38:23,641][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:38:24,149][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:38:24,657][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:38:25,165][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:38:25,673][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:38:26,180][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:38:26,686][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:38:27,195][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:38:27,702][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:38:28,209][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:38:28,716][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:38:29,223][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:38:29,732][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:38:30,242][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:38:30,750][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:38:31,258][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:38:31,766][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:38:32,274][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:38:32,782][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:38:33,291][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:38:33,799][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:38:34,306][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:38:34,814][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:38:35,323][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:38:35,831][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:38:36,340][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:38:36,848][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:38:37,356][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-26 00:38:38,010][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-26 00:38:38,753][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:38:38,755][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:38:38,757][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:38:39,480][__main__][INFO] - Iteration 416 took 1m 16s (9.96% Gen, 89.09% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 44m 10s. Estimated total time: 63h 47m 36s. Time estimates for 10 more iterations: 12m 45s, 100 more iterations: 2h 7m 35s, 500 more iterations: 10h 37m 56s. [2026-03-26 00:38:39,482][__main__][INFO] - Starting iteration 416. [2026-03-26 00:38:39,883][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:38:39,884][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:38:47,186][__main__][INFO] - Number of regex retries in iteration 416: 0 [2026-03-26 00:38:47,187][__main__][INFO] - agents played in iteration 416 are Bob, Alice [2026-03-26 00:38:48,152][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:38:48,772][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:38:49,236][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:38:49,751][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:38:50,260][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:38:50,767][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:38:51,276][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:38:51,784][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:38:52,292][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:38:52,801][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:38:53,312][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:38:53,821][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:38:54,329][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:38:54,838][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:38:55,347][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:38:55,855][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:38:56,364][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:38:56,873][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:38:57,382][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:38:57,891][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:38:58,399][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:38:58,909][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:38:59,418][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:38:59,926][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:39:00,435][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:39:00,943][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:39:01,454][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:39:01,964][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:39:02,474][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:39:02,983][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:39:03,493][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:39:04,002][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:39:04,512][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:39:05,022][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:39:05,533][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:39:06,041][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:39:06,551][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:39:07,059][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:39:07,568][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:39:08,076][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:39:08,586][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:39:09,094][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:39:09,602][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:39:10,112][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:39:10,622][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:39:11,132][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:39:11,641][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:39:12,151][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:39:12,660][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:39:13,170][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:39:13,697][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:39:14,211][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:39:14,721][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:39:15,233][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:39:15,744][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:39:16,254][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:39:16,765][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:39:17,275][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:39:17,784][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:39:18,293][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:39:18,802][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:39:19,311][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:39:19,821][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:39:20,330][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:39:20,839][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:39:21,348][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:39:21,856][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:39:22,364][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:39:22,872][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:39:23,381][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:39:23,889][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:39:24,398][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:39:24,905][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:39:25,415][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:39:25,924][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:39:26,433][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:39:26,942][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:39:27,452][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:39:27,961][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:39:28,469][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:39:28,978][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:39:29,486][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:39:29,995][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:39:30,503][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:39:31,013][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:39:31,522][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:39:32,031][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:39:32,541][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:39:33,049][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:39:33,559][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:39:34,069][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:39:34,579][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:39:35,089][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:39:35,598][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:39:36,107][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:39:36,616][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:39:37,126][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:39:37,636][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:39:38,145][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:39:38,654][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:39:39,162][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:39:39,672][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:39:40,182][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:39:40,692][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:39:41,202][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:39:41,711][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:39:42,221][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:39:42,732][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:39:43,242][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:39:43,752][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:39:44,262][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:39:44,772][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:39:45,281][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:39:45,791][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:39:46,303][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:39:46,814][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:39:47,325][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:39:47,836][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:39:48,348][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:39:48,860][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:39:49,371][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:39:49,883][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:39:50,394][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:39:50,902][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:39:51,413][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:39:51,922][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:39:52,432][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:39:52,943][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:39:53,452][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:39:53,963][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-26 00:39:54,623][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-26 00:39:55,374][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:39:55,376][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:39:55,378][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:39:56,060][__main__][INFO] - Iteration 417 took 1m 16s (9.59% Gen, 89.52% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 24m 9s. Estimated total time: 63h 28m 51s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 57s, 500 more iterations: 10h 34m 48s. [2026-03-26 00:39:56,062][__main__][INFO] - Starting iteration 417. [2026-03-26 00:39:56,463][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:39:56,464][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:40:03,487][__main__][INFO] - Number of regex retries in iteration 417: 0 [2026-03-26 00:40:03,488][__main__][INFO] - agents played in iteration 417 are Bob, Alice [2026-03-26 00:40:04,454][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:40:05,083][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:40:05,551][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:40:06,067][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:40:06,577][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:40:07,088][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:40:07,598][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:40:08,108][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:40:08,618][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:40:09,130][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:40:09,640][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:40:10,150][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:40:10,661][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:40:11,171][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:40:11,681][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:40:12,193][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:40:12,703][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:40:13,215][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:40:13,728][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:40:14,240][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:40:14,750][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:40:15,263][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:40:15,774][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:40:16,284][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:40:16,793][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:40:17,303][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:40:17,813][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:40:18,324][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:40:18,835][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:40:19,344][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:40:19,854][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:40:20,363][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:40:20,874][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:40:21,385][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:40:21,895][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:40:22,403][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:40:22,913][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:40:23,422][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:40:23,933][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:40:24,443][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:40:24,953][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:40:25,463][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:40:25,974][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:40:26,484][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:40:26,993][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:40:27,503][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:40:28,014][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:40:28,525][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:40:29,035][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:40:29,546][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:40:30,056][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:40:30,565][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:40:31,075][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:40:31,585][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:40:32,094][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:40:32,604][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:40:33,114][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:40:33,623][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:40:34,132][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:40:34,641][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:40:35,153][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:40:35,663][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:40:36,172][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:40:36,680][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:40:37,189][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:40:37,698][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:40:38,208][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:40:38,717][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:40:39,227][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:40:39,736][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:40:40,246][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:40:40,756][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:40:41,266][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:40:41,775][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:40:42,284][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:40:42,794][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:40:43,304][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:40:43,815][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:40:44,325][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:40:44,836][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:40:45,346][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:40:45,855][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:40:46,366][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:40:46,877][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:40:47,387][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:40:47,899][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:40:48,410][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:40:48,920][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:40:49,433][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:40:49,946][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:40:50,456][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:40:50,965][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:40:51,475][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:40:51,985][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:40:52,494][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:40:53,005][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:40:53,514][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:40:54,024][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:40:54,533][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:40:55,044][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:40:55,553][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:40:56,063][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:40:56,573][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:40:57,082][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:40:57,592][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:40:58,101][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:40:58,613][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:40:59,125][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:40:59,636][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:41:00,147][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:41:00,658][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:41:01,169][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:41:01,681][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:41:02,192][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:41:02,702][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:41:03,213][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:41:03,724][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:41:04,233][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:41:04,743][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:41:05,255][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:41:05,766][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:41:06,275][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:41:06,783][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:41:07,291][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:41:07,800][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:41:08,309][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:41:08,816][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:41:09,324][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:41:09,832][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:41:10,341][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 00:41:10,998][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:05 [2026-03-26 00:41:11,747][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:41:11,749][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:41:11,751][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:41:12,421][__main__][INFO] - Iteration 418 took 1m 15s (9.25% Gen, 89.87% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 11m 58s. Estimated total time: 63h 17m 57s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 35s, 500 more iterations: 10h 32m 59s. [2026-03-26 00:41:12,423][__main__][INFO] - Starting iteration 418. [2026-03-26 00:41:12,824][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:41:12,825][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:41:19,560][__main__][INFO] - Number of regex retries in iteration 418: 0 [2026-03-26 00:41:19,561][__main__][INFO] - agents played in iteration 418 are Bob, Alice [2026-03-26 00:41:20,526][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:41:21,152][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:41:21,614][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:41:22,127][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:41:22,635][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:41:23,143][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:41:23,650][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:41:24,159][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:41:24,667][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:41:25,173][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:41:25,684][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:41:26,191][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:41:26,700][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:41:27,208][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:41:27,718][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:41:28,226][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:41:28,735][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:41:29,244][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:41:29,754][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:41:30,262][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:41:30,769][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:41:31,278][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:41:31,786][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:41:32,294][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:41:32,802][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:41:33,310][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:41:33,822][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:41:34,332][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:41:34,842][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:41:35,354][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:41:35,864][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:41:36,374][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:41:36,883][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:41:37,393][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:41:37,902][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:41:38,412][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:41:38,921][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:41:39,431][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:41:39,941][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:41:40,451][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:41:40,959][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:41:41,469][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:41:41,978][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:41:42,487][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:41:42,995][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:41:43,503][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:41:44,012][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:41:44,520][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:41:45,030][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:41:45,539][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:41:46,047][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:41:46,555][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:41:47,064][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:41:47,572][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:41:48,079][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:41:48,587][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:41:49,096][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:41:49,604][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:41:50,112][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:41:50,620][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:41:51,129][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:41:51,637][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:41:52,145][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:41:52,655][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:41:53,163][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:41:53,672][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:41:54,180][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:41:54,687][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:41:55,194][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:41:55,701][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:41:56,212][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:41:56,721][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:41:57,229][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:41:57,737][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:41:58,246][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:41:58,756][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:41:59,265][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:41:59,775][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:42:00,284][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:42:00,792][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:42:01,301][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:42:01,813][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:42:02,322][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:42:02,830][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:42:03,339][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:42:03,847][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:42:04,355][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:42:04,863][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:42:05,373][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:42:05,882][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:42:06,392][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:42:06,903][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:42:07,415][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:42:07,927][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:42:08,438][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:42:08,949][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:42:09,461][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:42:09,972][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:42:10,481][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:42:10,992][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:42:11,502][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:42:12,014][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:42:12,524][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:42:13,034][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:42:13,544][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:42:14,054][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:42:14,564][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:42:15,074][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:42:15,583][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:42:16,094][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:42:16,604][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:42:17,114][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:42:17,623][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:42:18,133][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:42:18,643][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:42:19,153][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:42:19,662][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:42:20,172][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:42:20,682][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:42:21,190][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:42:21,700][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:42:22,210][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:42:22,720][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:42:23,230][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:42:23,740][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:42:24,250][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:42:24,760][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:42:25,270][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:42:25,779][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:42:26,289][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-26 00:42:26,947][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.38%, ΔTime: 00:01:05 [2026-03-26 00:42:27,692][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:42:27,694][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:42:27,695][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:42:28,382][__main__][INFO] - Iteration 419 took 1m 15s (8.92% Gen, 90.17% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 50m 41s. Estimated total time: 62h 57m 56s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 55s, 500 more iterations: 10h 29m 39s. [2026-03-26 00:42:28,384][__main__][INFO] - Starting iteration 419. [2026-03-26 00:42:28,787][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:42:28,788][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:42:32,450][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:42:36,120][__main__][INFO] - Number of regex retries in iteration 419: 1 [2026-03-26 00:42:36,121][__main__][INFO] - agents played in iteration 419 are Bob, Alice [2026-03-26 00:42:37,084][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:42:37,716][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:42:38,181][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:42:38,695][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:42:39,205][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:42:39,714][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:42:40,224][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:42:40,734][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:42:41,245][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:42:41,756][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:42:42,265][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:42:42,774][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:42:43,283][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:42:43,792][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:42:44,300][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:42:44,809][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:42:45,317][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:42:45,826][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:42:46,336][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:42:46,846][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:42:47,354][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:42:47,863][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:42:48,373][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:42:48,881][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:42:49,390][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:42:49,899][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:42:50,409][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:42:50,917][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:42:51,426][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:42:51,936][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:42:52,447][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:42:52,955][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:42:53,464][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:42:53,973][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:42:54,487][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:42:54,999][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:42:55,510][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:42:56,023][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:42:56,535][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:42:57,046][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:42:57,558][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:42:58,070][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:42:58,579][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:42:59,089][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:42:59,598][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:43:00,106][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:43:00,616][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:43:01,125][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:43:01,634][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:43:02,143][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:43:02,653][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:43:03,162][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:43:03,671][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:43:04,181][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:43:04,691][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:43:05,200][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:43:05,708][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:43:06,219][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:43:06,730][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:43:07,240][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:43:07,752][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:43:08,261][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:43:08,771][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:43:09,280][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:43:09,789][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:43:10,299][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:43:10,809][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:43:11,319][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:43:11,830][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:43:12,341][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:43:12,851][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:43:13,360][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:43:13,870][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:43:14,381][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:43:14,892][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:43:15,402][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:43:15,909][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:43:16,418][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:43:16,928][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:43:17,436][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:43:17,944][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:43:18,454][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:43:18,962][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:43:19,471][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:43:19,979][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:43:20,487][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:43:20,996][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:43:21,504][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:43:22,014][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:43:22,522][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:43:23,033][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:43:23,542][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:43:24,053][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:43:24,562][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:43:25,072][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:43:25,581][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:43:26,093][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:43:26,603][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:43:27,115][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:43:27,628][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:43:28,142][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:43:28,654][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:43:29,166][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:43:29,679][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:43:30,191][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:43:30,702][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:43:31,213][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:43:31,722][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:43:32,233][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:43:32,744][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:43:33,253][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:43:33,763][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:43:34,271][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:43:34,781][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:43:35,291][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:43:35,800][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:43:36,313][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:43:36,825][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:43:37,335][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:43:37,845][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:43:38,356][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:43:38,866][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:43:39,376][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:43:39,886][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:43:40,397][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:43:40,907][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:43:41,416][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:43:41,927][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:43:42,437][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:43:42,946][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21747 tokens. [2026-03-26 00:43:43,612][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.53%, ΔTime: 00:01:05 [2026-03-26 00:43:44,369][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:43:44,371][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:43:44,373][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:43:45,264][__main__][INFO] - Iteration 420 took 1m 16s (9.59% Gen, 89.24% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 35m 19s. Estimated total time: 63h 43m 51s. Time estimates for 10 more iterations: 12m 44s, 100 more iterations: 2h 7m 27s, 500 more iterations: 10h 37m 18s. [2026-03-26 00:43:45,266][__main__][INFO] - Starting iteration 420. [2026-03-26 00:43:45,669][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:43:45,670][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:43:47,023][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:43:48,902][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:43:53,339][__main__][INFO] - Number of regex retries in iteration 420: 2 [2026-03-26 00:43:53,339][__main__][INFO] - agents played in iteration 420 are Bob, Alice [2026-03-26 00:43:54,300][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:43:54,940][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:43:55,407][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:43:55,922][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:43:56,431][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:43:56,941][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:43:57,451][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:43:57,960][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:43:58,468][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:43:58,977][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:43:59,486][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:43:59,996][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:44:00,505][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:44:01,015][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:44:01,524][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:44:02,032][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:44:02,542][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:44:03,054][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:44:03,563][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:44:04,071][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:44:04,581][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:44:05,091][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:44:05,602][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:44:06,113][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:44:06,623][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:44:07,133][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:44:07,642][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:44:08,152][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:44:08,661][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:44:09,169][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:44:09,676][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:44:10,184][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:44:10,692][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:44:11,201][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:44:11,712][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:44:12,222][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:44:12,732][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:44:13,243][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:44:13,751][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:44:14,258][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:44:14,768][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:44:15,276][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:44:15,783][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:44:16,290][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:44:16,796][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:44:17,302][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:44:17,809][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:44:18,315][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:44:18,824][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:44:19,332][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:44:19,844][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:44:20,353][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:44:20,864][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:44:21,374][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:44:21,883][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:44:22,394][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:44:22,904][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:44:23,414][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:44:23,921][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:44:24,427][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:44:24,932][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:44:25,438][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:44:25,945][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:44:26,454][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:44:26,961][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:44:27,467][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:44:27,976][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:44:28,485][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:44:28,995][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:44:29,503][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:44:30,012][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:44:30,521][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:44:31,031][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:44:31,541][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:44:32,051][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:44:32,560][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:44:33,068][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:44:33,577][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:44:34,087][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:44:34,596][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:44:35,103][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:44:35,613][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:44:36,121][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:44:36,630][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:44:37,139][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:44:37,647][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:44:38,155][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:44:38,663][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:44:39,172][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:44:39,682][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:44:40,189][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:44:40,697][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:44:41,205][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:44:41,713][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:44:42,222][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:44:42,731][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:44:43,239][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:44:43,747][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:44:44,256][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:44:44,766][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:44:45,276][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:44:45,784][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:44:46,292][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:44:46,802][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:44:47,311][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:44:47,821][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:44:48,333][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:44:48,841][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:44:49,350][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:44:49,858][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:44:50,367][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:44:50,875][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:44:51,383][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:44:51,891][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:44:52,400][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:44:52,911][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:44:53,421][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:44:53,932][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:44:54,442][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:44:54,951][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:44:55,461][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:44:55,970][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:44:56,475][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:44:56,980][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:44:57,485][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:44:57,991][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:44:58,496][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:44:59,089][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:44:59,597][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:45:00,102][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21624 tokens. [2026-03-26 00:45:00,772][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.16%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.40%, ΔTime: 00:01:05 [2026-03-26 00:45:01,521][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:45:01,524][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:45:01,525][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:45:02,192][__main__][INFO] - Iteration 421 took 1m 16s (10.02% Gen, 89.10% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 36m 21s. Estimated total time: 63h 46m 10s. Time estimates for 10 more iterations: 12m 45s, 100 more iterations: 2h 7m 32s, 500 more iterations: 10h 37m 41s. [2026-03-26 00:45:02,194][__main__][INFO] - Starting iteration 421. [2026-03-26 00:45:02,598][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:45:02,599][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:45:09,043][__main__][INFO] - Number of regex retries in iteration 421: 0 [2026-03-26 00:45:09,044][__main__][INFO] - agents played in iteration 421 are Bob, Alice [2026-03-26 00:45:10,002][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:45:10,630][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:45:11,094][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:45:11,609][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:45:12,118][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:45:12,626][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:45:13,135][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:45:13,644][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:45:14,152][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:45:14,661][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:45:15,170][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:45:15,678][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:45:16,186][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:45:16,694][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:45:17,202][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:45:17,710][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:45:18,217][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:45:18,726][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:45:19,238][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:45:19,747][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:45:20,257][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:45:20,766][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:45:21,275][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:45:21,784][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:45:22,294][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:45:22,804][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:45:23,313][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:45:23,821][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:45:24,331][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:45:24,840][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:45:25,348][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:45:25,857][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:45:26,365][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:45:26,874][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:45:27,383][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:45:27,895][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:45:28,404][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:45:28,913][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:45:29,421][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:45:29,932][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:45:30,441][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:45:30,950][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:45:31,458][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:45:31,967][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:45:32,475][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:45:32,984][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:45:33,495][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:45:34,004][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:45:34,514][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:45:35,023][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:45:35,533][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:45:36,043][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:45:36,552][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:45:37,062][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:45:37,572][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:45:38,081][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:45:38,590][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:45:39,099][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:45:39,612][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:45:40,122][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:45:40,635][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:45:41,146][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:45:41,656][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:45:42,165][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:45:42,675][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:45:43,185][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:45:43,690][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:45:44,196][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:45:44,704][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:45:45,213][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:45:45,722][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:45:46,233][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:45:46,742][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:45:47,250][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:45:47,758][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:45:48,265][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:45:48,773][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:45:49,281][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:45:49,787][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:45:50,296][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:45:50,804][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:45:51,312][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:45:51,821][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:45:52,331][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:45:52,841][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:45:53,350][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:45:53,859][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:45:54,369][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:45:54,878][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:45:55,387][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:45:55,895][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:45:56,403][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:45:56,909][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:45:57,417][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:45:57,925][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:45:58,434][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:45:58,942][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:45:59,450][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:45:59,959][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:46:00,469][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:46:00,977][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:46:01,485][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:46:01,994][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:46:02,502][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:46:03,012][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:46:03,521][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:46:04,031][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:46:04,539][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:46:05,048][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:46:05,556][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:46:06,065][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:46:06,573][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:46:07,081][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:46:07,591][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:46:08,100][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:46:08,607][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:46:09,113][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:46:09,623][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:46:10,133][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:46:10,643][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:46:11,155][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:46:11,666][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:46:12,176][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:46:12,686][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:46:13,196][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:46:13,705][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:46:14,216][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:46:14,727][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:46:15,240][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:46:15,750][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-26 00:46:16,422][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.65%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 00:46:17,174][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:46:17,176][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:46:17,177][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:46:17,932][__main__][INFO] - Iteration 422 took 1m 15s (8.55% Gen, 90.44% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 35m 37s. Estimated total time: 62h 46m 42s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 33s, 500 more iterations: 10h 27m 47s. [2026-03-26 00:46:17,934][__main__][INFO] - Starting iteration 422. [2026-03-26 00:46:18,346][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:46:18,347][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:46:25,529][__main__][INFO] - Number of regex retries in iteration 422: 0 [2026-03-26 00:46:25,530][__main__][INFO] - agents played in iteration 422 are Bob, Alice [2026-03-26 00:46:26,639][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:46:27,273][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:46:27,737][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:46:28,252][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:46:28,761][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:46:29,268][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:46:29,777][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:46:30,286][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:46:30,795][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:46:31,304][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:46:31,814][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:46:32,323][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:46:32,833][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:46:33,343][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:46:33,853][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:46:34,363][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:46:34,872][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:46:35,381][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:46:35,893][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:46:36,403][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:46:36,915][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:46:37,426][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:46:37,937][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:46:38,448][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:46:38,959][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:46:39,469][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:46:39,978][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:46:40,488][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:46:40,998][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:46:41,507][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:46:42,017][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:46:42,527][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:46:43,036][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:46:43,547][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:46:44,057][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:46:44,566][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:46:45,076][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:46:45,585][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:46:46,095][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:46:46,604][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:46:47,115][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:46:47,624][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:46:48,137][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:46:48,648][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:46:49,159][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:46:49,670][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:46:50,181][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:46:50,693][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:46:51,204][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:46:51,715][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:46:52,225][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:46:52,737][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:46:53,249][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:46:53,760][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:46:54,270][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:46:54,780][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:46:55,290][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:46:55,800][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:46:56,311][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:46:56,821][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:46:57,333][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:46:57,843][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:46:58,353][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:46:58,863][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:46:59,374][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:46:59,884][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:47:00,392][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:47:00,900][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:47:01,412][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:47:01,922][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:47:02,431][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:47:02,941][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:47:03,451][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:47:03,961][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:47:04,470][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:47:04,979][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:47:05,491][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:47:06,001][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:47:06,511][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:47:07,022][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:47:07,532][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:47:08,042][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:47:08,555][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:47:09,066][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:47:09,576][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:47:10,087][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:47:10,598][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:47:11,108][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:47:11,618][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:47:12,131][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:47:12,642][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:47:13,151][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:47:13,661][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:47:14,172][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:47:14,683][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:47:15,194][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:47:15,704][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:47:16,214][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:47:16,724][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:47:17,236][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:47:17,747][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:47:18,257][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:47:18,767][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:47:19,277][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:47:19,788][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:47:20,297][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:47:20,810][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:47:21,322][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:47:21,835][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:47:22,347][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:47:22,860][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:47:23,371][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:47:23,883][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:47:24,395][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:47:24,906][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:47:25,416][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:47:25,926][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:47:26,437][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:47:26,947][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:47:27,458][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:47:27,968][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:47:28,478][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:47:28,989][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:47:29,500][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:47:30,009][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:47:30,519][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:47:31,033][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:47:31,543][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:47:32,053][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:47:32,564][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-26 00:47:33,228][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 00:47:33,980][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:47:33,982][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:47:33,984][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:47:34,658][__main__][INFO] - Iteration 423 took 1m 16s (9.41% Gen, 89.70% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 23m 16s. Estimated total time: 63h 35m 37s. Time estimates for 10 more iterations: 12m 43s, 100 more iterations: 2h 7m 11s, 500 more iterations: 10h 35m 56s. [2026-03-26 00:47:34,660][__main__][INFO] - Starting iteration 423. [2026-03-26 00:47:35,064][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:47:35,065][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:47:35,710][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:47:41,719][__main__][INFO] - Number of regex retries in iteration 423: 1 [2026-03-26 00:47:41,720][__main__][INFO] - agents played in iteration 423 are Bob, Alice [2026-03-26 00:47:42,685][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:47:43,612][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:47:44,077][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:47:44,592][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:47:45,101][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:47:45,612][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:47:46,121][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:47:46,631][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:47:47,141][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:47:47,650][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:47:48,159][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:47:48,668][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:47:49,177][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:47:49,685][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:47:50,194][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:47:50,703][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:47:51,213][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:47:51,723][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:47:52,234][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:47:52,744][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:47:53,252][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:47:53,761][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:47:54,271][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:47:54,780][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:47:55,287][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:47:55,795][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:47:56,303][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:47:56,813][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:47:57,321][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:47:57,833][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:47:58,342][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:47:58,852][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:47:59,361][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:47:59,870][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:48:00,382][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:48:00,892][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:48:01,401][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:48:01,913][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:48:02,423][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:48:02,934][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:48:03,445][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:48:03,955][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:48:04,467][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:48:04,977][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:48:05,487][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:48:05,997][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:48:06,507][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:48:07,017][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:48:07,526][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:48:08,037][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:48:08,547][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:48:09,057][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:48:09,567][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:48:10,077][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:48:10,587][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:48:11,096][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:48:11,605][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:48:12,116][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:48:12,627][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:48:13,138][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:48:13,649][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:48:14,160][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:48:14,670][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:48:15,179][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:48:15,690][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:48:16,200][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:48:16,711][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:48:17,219][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:48:17,728][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:48:18,238][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:48:18,747][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:48:19,256][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:48:19,765][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:48:20,273][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:48:20,782][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:48:21,292][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:48:21,801][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:48:22,312][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:48:22,821][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:48:23,331][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:48:23,841][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:48:24,351][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:48:24,859][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:48:25,368][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:48:25,877][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:48:26,386][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:48:26,895][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:48:27,404][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:48:27,914][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:48:28,423][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:48:28,933][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:48:29,442][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:48:29,950][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:48:30,460][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:48:30,968][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:48:31,475][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:48:31,983][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:48:32,492][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:48:33,001][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:48:33,511][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:48:34,023][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:48:34,534][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:48:35,045][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:48:35,554][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:48:36,064][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:48:36,574][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:48:37,084][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:48:37,595][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:48:38,106][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:48:38,617][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:48:39,127][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:48:39,637][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:48:40,147][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:48:40,658][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:48:41,169][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:48:41,675][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:48:42,185][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:48:42,695][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:48:43,204][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:48:43,713][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:48:44,223][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:48:44,734][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:48:45,246][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:48:45,757][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:48:46,267][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:48:46,778][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:48:47,288][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:48:47,798][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:48:48,310][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:48:48,821][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21718 tokens. [2026-03-26 00:48:49,487][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-26 00:48:50,246][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:48:50,248][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:48:50,250][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:48:50,918][__main__][INFO] - Iteration 424 took 1m 15s (8.77% Gen, 90.34% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 59m 6s. Estimated total time: 63h 12m 44s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 25s, 500 more iterations: 10h 32m 7s. [2026-03-26 00:48:50,921][__main__][INFO] - Starting iteration 424. [2026-03-26 00:48:51,322][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:48:51,323][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:48:57,315][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:48:58,989][__main__][INFO] - Number of regex retries in iteration 424: 1 [2026-03-26 00:48:58,989][__main__][INFO] - agents played in iteration 424 are Bob, Alice [2026-03-26 00:48:59,959][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:49:00,599][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:49:01,063][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:49:01,577][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:49:02,085][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:49:02,594][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:49:03,103][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:49:03,612][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:49:04,122][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:49:04,632][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:49:05,145][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:49:05,655][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:49:06,164][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:49:06,674][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:49:07,185][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:49:07,695][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:49:08,205][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:49:08,715][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:49:09,224][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:49:09,734][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:49:10,243][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:49:10,753][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:49:11,262][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:49:11,772][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:49:12,281][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:49:12,791][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:49:13,301][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:49:13,810][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:49:14,319][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:49:14,828][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:49:15,338][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:49:15,847][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:49:16,357][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:49:16,867][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:49:17,375][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:49:17,884][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:49:18,392][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:49:18,900][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:49:19,409][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:49:19,917][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:49:20,425][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:49:20,933][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:49:21,444][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:49:21,954][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:49:22,464][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:49:22,974][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:49:23,484][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:49:23,995][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:49:24,504][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:49:25,013][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:49:25,522][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:49:26,033][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:49:26,544][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:49:27,053][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:49:27,563][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:49:28,073][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:49:28,582][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:49:29,092][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:49:29,602][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:49:30,113][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:49:30,623][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:49:31,135][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:49:31,647][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:49:32,158][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:49:32,667][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:49:33,178][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:49:33,687][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:49:34,196][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:49:34,705][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:49:35,214][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:49:35,723][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:49:36,233][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:49:36,742][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:49:37,252][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:49:37,763][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:49:38,272][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:49:38,782][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:49:39,292][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:49:39,802][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:49:40,315][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:49:40,826][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:49:41,336][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:49:41,846][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:49:42,355][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:49:42,864][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:49:43,373][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:49:43,882][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:49:44,391][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:49:44,900][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:49:45,409][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:49:45,918][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:49:46,427][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:49:46,935][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:49:47,444][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:49:47,953][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:49:48,462][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:49:48,970][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:49:49,478][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:49:49,987][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:49:50,495][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:49:51,003][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:49:51,514][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:49:52,023][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:49:52,532][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:49:53,040][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:49:53,550][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:49:54,060][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:49:54,570][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:49:55,079][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:49:55,587][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:49:56,096][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:49:56,605][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:49:57,115][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:49:57,625][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:49:58,134][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:49:58,643][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:49:59,154][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:49:59,664][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:50:00,173][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:50:00,683][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:50:01,192][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:50:01,702][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:50:02,212][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:50:02,722][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:50:03,231][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:50:03,740][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:50:04,250][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:50:04,758][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:50:05,267][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:50:05,775][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21743 tokens. [2026-03-26 00:50:06,446][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 00:50:07,197][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:50:07,200][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:50:07,201][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:50:07,869][__main__][INFO] - Iteration 425 took 1m 16s (10.02% Gen, 89.11% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 32m 27s. Estimated total time: 63h 47m 22s. Time estimates for 10 more iterations: 12m 45s, 100 more iterations: 2h 7m 34s, 500 more iterations: 10h 37m 53s. [2026-03-26 00:50:07,871][__main__][INFO] - Starting iteration 425. [2026-03-26 00:50:08,272][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:50:08,273][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:50:08,915][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:50:09,321][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 2/3 [2026-03-26 00:50:13,473][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:50:15,001][__main__][INFO] - Number of regex retries in iteration 425: 3 [2026-03-26 00:50:15,002][__main__][INFO] - agents played in iteration 425 are Bob, Alice [2026-03-26 00:50:15,972][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:50:16,612][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:50:17,079][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:50:17,593][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:50:18,102][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:50:18,612][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:50:19,123][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:50:19,632][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:50:20,143][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:50:20,653][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:50:21,169][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:50:21,679][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:50:22,188][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:50:22,696][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:50:23,205][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:50:23,716][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:50:24,225][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:50:24,735][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:50:25,245][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:50:25,755][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:50:26,264][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:50:26,773][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:50:27,282][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:50:27,790][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:50:28,299][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:50:28,807][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:50:29,316][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:50:29,825][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:50:30,334][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:50:30,843][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:50:31,351][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:50:31,860][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:50:32,368][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:50:32,876][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:50:33,388][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:50:33,896][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:50:34,404][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:50:34,915][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:50:35,424][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:50:35,934][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:50:36,443][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:50:36,953][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:50:37,462][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:50:37,971][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:50:38,480][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:50:38,989][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:50:39,497][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:50:40,005][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:50:40,515][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:50:41,025][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:50:41,535][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:50:42,043][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:50:42,553][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:50:43,062][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:50:43,573][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:50:44,082][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:50:44,590][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:50:45,099][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:50:45,608][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:50:46,118][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:50:46,628][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:50:47,138][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:50:47,648][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:50:48,156][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:50:48,668][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:50:49,177][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:50:49,686][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:50:50,194][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:50:50,702][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:50:51,211][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:50:51,720][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:50:52,228][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:50:52,737][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:50:53,245][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:50:53,754][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:50:54,263][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:50:54,773][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:50:55,282][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:50:55,791][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:50:56,300][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:50:56,810][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:50:57,318][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:50:57,827][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:50:58,337][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:50:58,845][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:50:59,354][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:50:59,863][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:51:00,372][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:51:00,881][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:51:01,390][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:51:01,898][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:51:02,406][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:51:02,916][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:51:03,425][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:51:03,934][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:51:04,442][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:51:04,951][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:51:05,459][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:51:05,969][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:51:06,479][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:51:06,989][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:51:07,499][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:51:08,009][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:51:08,520][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:51:09,031][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:51:09,541][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:51:10,051][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:51:10,560][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:51:11,068][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:51:11,578][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:51:12,087][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:51:12,596][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:51:13,105][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:51:13,613][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:51:14,122][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:51:14,633][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:51:15,143][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:51:15,657][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:51:16,167][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:51:16,678][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:51:17,189][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:51:17,700][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:51:18,211][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:51:18,721][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:51:19,233][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:51:19,746][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:51:20,259][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:51:20,771][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:51:21,281][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:51:21,792][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21745 tokens. [2026-03-26 00:51:22,470][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-26 00:51:23,224][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:51:23,227][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:51:23,228][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:51:23,974][__main__][INFO] - Iteration 426 took 1m 15s (8.89% Gen, 90.12% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 48m 56s. Estimated total time: 63h 5m 7s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 10s, 500 more iterations: 10h 30m 51s. [2026-03-26 00:51:23,976][__main__][INFO] - Starting iteration 426. [2026-03-26 00:51:24,380][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:51:24,381][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:51:29,332][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:51:31,544][__main__][INFO] - Number of regex retries in iteration 426: 1 [2026-03-26 00:51:31,545][__main__][INFO] - agents played in iteration 426 are Bob, Alice [2026-03-26 00:51:32,510][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:51:33,152][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:51:33,620][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:51:34,136][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:51:34,649][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:51:35,160][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:51:35,672][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:51:36,184][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:51:36,695][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:51:37,206][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:51:37,715][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:51:38,224][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:51:38,736][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:51:39,246][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:51:39,757][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:51:40,267][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:51:40,777][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:51:41,286][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:51:41,795][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:51:42,304][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:51:42,815][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:51:43,326][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:51:43,836][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:51:44,346][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:51:44,855][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:51:45,365][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:51:45,873][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:51:46,382][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:51:46,891][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:51:47,399][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:51:47,907][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:51:48,415][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:51:48,924][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:51:49,434][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:51:49,942][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:51:50,453][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:51:50,962][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:51:51,471][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:51:51,979][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:51:52,488][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:51:52,997][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:51:53,505][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:51:54,016][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:51:54,527][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:51:55,038][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:51:55,548][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:51:56,058][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:51:56,568][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:51:57,078][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:51:57,589][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:51:58,098][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:51:58,607][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:51:59,116][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:51:59,625][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:52:00,133][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:52:00,642][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:52:01,153][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:52:01,662][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:52:02,171][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:52:02,680][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:52:03,189][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:52:03,698][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:52:04,207][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:52:04,716][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:52:05,225][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:52:05,734][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:52:06,245][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:52:06,757][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:52:07,269][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:52:07,779][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:52:08,291][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:52:08,801][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:52:09,312][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:52:09,823][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:52:10,332][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:52:10,842][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:52:11,350][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:52:11,859][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:52:12,367][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:52:12,876][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:52:13,384][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:52:13,895][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:52:14,404][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:52:14,914][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:52:15,423][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:52:15,933][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:52:16,443][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:52:16,953][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:52:17,461][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:52:17,972][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:52:18,480][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:52:18,989][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:52:19,497][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:52:20,005][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:52:20,514][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:52:21,022][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:52:21,531][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:52:22,040][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:52:22,548][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:52:23,056][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:52:23,564][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:52:24,072][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:52:24,581][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:52:25,092][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:52:25,601][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:52:26,109][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:52:26,618][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:52:27,129][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:52:27,638][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:52:28,147][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:52:28,657][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:52:29,166][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:52:29,676][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:52:30,185][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:52:30,695][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:52:31,204][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:52:31,713][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:52:32,222][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:52:32,732][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:52:33,241][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:52:33,750][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:52:34,259][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:52:34,768][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:52:35,275][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:52:35,783][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:52:36,295][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:52:36,804][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:52:37,314][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:52:37,823][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:52:38,333][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21736 tokens. [2026-03-26 00:52:39,001][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:05 [2026-03-26 00:52:39,757][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:52:39,759][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:52:39,761][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:52:40,507][__main__][INFO] - Iteration 427 took 1m 16s (9.41% Gen, 89.61% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 8m 56s. Estimated total time: 63h 26m 23s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 52s, 500 more iterations: 10h 34m 23s. [2026-03-26 00:52:40,509][__main__][INFO] - Starting iteration 427. [2026-03-26 00:52:40,910][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:52:40,910][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:52:42,139][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:52:47,873][__main__][INFO] - Number of regex retries in iteration 427: 1 [2026-03-26 00:52:47,874][__main__][INFO] - agents played in iteration 427 are Bob, Alice [2026-03-26 00:52:48,826][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:52:49,461][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:52:49,928][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:52:50,443][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:52:50,954][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:52:51,464][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:52:51,975][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:52:52,485][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:52:52,996][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:52:53,504][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:52:54,013][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:52:54,522][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:52:55,032][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:52:55,542][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:52:56,051][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:52:56,561][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:52:57,070][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:52:57,578][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:52:58,086][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:52:58,595][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:52:59,101][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:52:59,610][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:53:00,118][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:53:00,626][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:53:01,134][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:53:01,642][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:53:02,154][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:53:02,665][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:53:03,176][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:53:03,687][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:53:04,197][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:53:04,706][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:53:05,216][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:53:05,727][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:53:06,236][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:53:06,745][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:53:07,254][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:53:07,763][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:53:08,271][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:53:08,781][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:53:09,289][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:53:09,798][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:53:10,308][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:53:10,817][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:53:11,325][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:53:11,836][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:53:12,346][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:53:12,857][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:53:13,365][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:53:13,874][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:53:14,381][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:53:14,889][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:53:15,397][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:53:15,904][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:53:16,412][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:53:16,920][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:53:17,427][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:53:17,934][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:53:18,442][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:53:18,952][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:53:19,460][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:53:19,968][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:53:20,476][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:53:20,985][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:53:21,493][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:53:22,001][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:53:22,511][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:53:23,020][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:53:23,530][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:53:24,039][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:53:24,548][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:53:25,057][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:53:25,565][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:53:26,075][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:53:26,583][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:53:27,091][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:53:27,600][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:53:28,108][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:53:28,616][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:53:29,124][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:53:29,635][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:53:30,145][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:53:30,652][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:53:31,161][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:53:31,669][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:53:32,176][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:53:32,685][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:53:33,192][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:53:33,700][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:53:34,207][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:53:34,716][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:53:35,226][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:53:35,735][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:53:36,245][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:53:36,755][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:53:37,265][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:53:37,774][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:53:38,285][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:53:38,795][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:53:39,306][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:53:39,816][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:53:40,326][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:53:40,836][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:53:41,347][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:53:41,856][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:53:42,366][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:53:42,875][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:53:43,384][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:53:43,899][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:53:44,410][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:53:44,921][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:53:45,432][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:53:45,943][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:53:46,453][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:53:46,964][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:53:47,474][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:53:47,984][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:53:48,494][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:53:49,004][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:53:49,516][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:53:50,027][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:53:50,537][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:53:51,047][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:53:51,557][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:53:52,067][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:53:52,584][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:53:53,094][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:53:53,605][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:53:54,115][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:53:54,626][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 00:53:55,294][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 00:53:56,038][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:53:56,041][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:53:56,042][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:53:56,922][__main__][INFO] - Iteration 428 took 1m 16s (9.16% Gen, 89.68% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 54h 1m 54s. Estimated total time: 63h 20m 38s. Time estimates for 10 more iterations: 12m 40s, 100 more iterations: 2h 6m 41s, 500 more iterations: 10h 33m 26s. [2026-03-26 00:53:56,924][__main__][INFO] - Starting iteration 428. [2026-03-26 00:53:57,326][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:53:57,327][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:54:02,213][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:54:03,952][__main__][INFO] - Number of regex retries in iteration 428: 1 [2026-03-26 00:54:03,953][__main__][INFO] - agents played in iteration 428 are Bob, Alice [2026-03-26 00:54:04,901][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:54:05,524][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:54:05,988][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:54:06,500][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:54:07,007][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:54:07,516][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:54:08,022][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:54:08,530][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:54:09,039][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:54:09,547][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:54:10,057][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:54:10,565][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:54:11,074][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:54:11,582][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:54:12,090][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:54:12,597][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:54:13,106][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:54:13,614][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:54:14,124][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:54:14,632][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:54:15,141][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:54:15,650][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:54:16,158][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:54:16,665][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:54:17,174][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:54:17,682][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:54:18,192][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:54:18,702][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:54:19,212][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:54:19,721][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:54:20,230][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:54:20,740][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:54:21,249][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:54:21,758][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:54:22,289][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:54:22,802][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:54:23,311][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:54:23,821][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:54:24,331][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:54:24,841][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:54:25,353][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:54:25,864][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:54:26,373][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:54:26,882][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:54:27,391][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:54:27,900][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:54:28,408][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:54:28,916][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:54:29,425][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:54:29,934][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:54:30,443][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:54:30,954][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:54:31,463][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:54:31,971][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:54:32,481][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:54:32,990][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:54:33,498][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:54:34,007][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:54:34,515][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:54:35,024][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:54:35,533][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:54:36,042][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:54:36,552][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:54:37,062][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:54:37,570][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:54:38,078][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:54:38,585][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:54:39,093][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:54:39,601][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:54:40,107][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:54:40,616][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:54:41,124][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:54:41,632][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:54:42,140][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:54:42,649][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:54:43,157][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:54:43,665][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:54:44,174][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:54:44,682][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:54:45,191][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:54:45,699][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:54:46,207][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:54:46,715][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:54:47,222][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:54:47,730][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:54:48,239][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:54:48,747][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:54:49,256][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:54:49,764][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:54:50,274][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:54:50,782][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:54:51,290][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:54:51,798][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:54:52,306][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:54:52,814][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:54:53,322][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:54:53,833][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:54:54,341][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:54:54,850][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:54:55,361][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:54:55,870][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:54:56,380][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:54:56,889][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:54:57,398][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:54:57,907][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:54:58,417][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:54:58,926][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:54:59,435][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:54:59,945][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:55:00,454][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:55:00,961][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:55:01,469][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:55:01,978][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:55:02,488][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:55:02,996][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:55:03,505][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:55:04,014][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:55:04,523][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:55:05,032][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:55:05,541][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:55:06,056][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:55:06,582][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:55:07,098][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:55:07,609][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:55:08,121][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:55:08,634][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:55:09,146][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:55:09,658][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:55:10,169][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:55:10,680][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 00:55:11,340][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-26 00:55:12,085][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:55:12,087][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:55:12,089][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:55:12,836][__main__][INFO] - Iteration 429 took 1m 15s (8.77% Gen, 90.23% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 35m 33s. Estimated total time: 62h 55m 32s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 51s, 500 more iterations: 10h 29m 15s. [2026-03-26 00:55:12,838][__main__][INFO] - Starting iteration 429. [2026-03-26 00:55:13,241][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:55:13,242][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:55:13,881][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:55:15,841][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:55:19,379][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:55:21,195][__main__][INFO] - Number of regex retries in iteration 429: 3 [2026-03-26 00:55:21,196][__main__][INFO] - agents played in iteration 429 are Bob, Alice [2026-03-26 00:55:22,161][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:55:22,789][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:55:23,253][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:55:23,767][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:55:24,275][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:55:24,782][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:55:25,292][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:55:25,799][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:55:26,305][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:55:26,816][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:55:27,329][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:55:27,841][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:55:28,354][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:55:28,866][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:55:29,376][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:55:29,887][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:55:30,397][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:55:30,907][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:55:31,417][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:55:31,927][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:55:32,438][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:55:32,947][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:55:33,457][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:55:33,965][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:55:34,474][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:55:34,982][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:55:35,491][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:55:35,998][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:55:36,506][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:55:37,015][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:55:37,524][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:55:38,034][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:55:38,542][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:55:39,050][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:55:39,556][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:55:40,063][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:55:40,569][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:55:41,075][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:55:41,581][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:55:42,086][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:55:42,592][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:55:43,099][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:55:43,608][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:55:44,117][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:55:44,624][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:55:45,134][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:55:45,644][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:55:46,153][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:55:46,662][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:55:47,171][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:55:47,679][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:55:48,187][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:55:48,695][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:55:49,202][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:55:49,712][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:55:50,219][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:55:50,727][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:55:51,236][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:55:51,744][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:55:52,254][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:55:52,763][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:55:53,272][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:55:53,782][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:55:54,290][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:55:54,798][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:55:55,307][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:55:55,815][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:55:56,324][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:55:56,833][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:55:57,341][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:55:57,851][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:55:58,359][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:55:58,869][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:55:59,377][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:55:59,886][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:56:00,397][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:56:00,909][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:56:01,419][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:56:01,930][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:56:02,442][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:56:02,953][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:56:03,464][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:56:03,974][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:56:04,483][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:56:04,993][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:56:05,502][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:56:06,013][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:56:06,522][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:56:07,031][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:56:07,540][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:56:08,048][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:56:08,556][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:56:09,065][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:56:09,573][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:56:10,080][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:56:10,588][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:56:11,096][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:56:11,605][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:56:12,110][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:56:12,617][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:56:13,123][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:56:13,628][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:56:14,135][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:56:14,640][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:56:15,146][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:56:15,652][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:56:16,161][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:56:16,671][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:56:17,180][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:56:17,688][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:56:18,197][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:56:18,706][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:56:19,215][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:56:19,723][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:56:20,233][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:56:20,741][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:56:21,250][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:56:21,758][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:56:22,266][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:56:22,774][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:56:23,282][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:56:23,790][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:56:24,299][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:56:24,807][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:56:25,316][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:56:25,825][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:56:26,334][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:56:26,843][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:56:27,352][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:56:27,861][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21745 tokens. [2026-03-26 00:56:28,540][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:05 [2026-03-26 00:56:29,292][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:56:29,294][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:56:29,296][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:56:30,029][__main__][INFO] - Iteration 430 took 1m 16s (10.36% Gen, 88.68% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 38m 8s. Estimated total time: 63h 59m 25s. Time estimates for 10 more iterations: 12m 47s, 100 more iterations: 2h 7m 58s, 500 more iterations: 10h 39m 54s. [2026-03-26 00:56:30,033][__main__][INFO] - Starting iteration 430. [2026-03-26 00:56:30,437][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:56:30,438][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:56:33,450][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:56:37,318][__main__][INFO] - Number of regex retries in iteration 430: 1 [2026-03-26 00:56:37,319][__main__][INFO] - agents played in iteration 430 are Bob, Alice [2026-03-26 00:56:38,284][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:56:38,916][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:56:39,383][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:56:39,897][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:56:40,407][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:56:40,916][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:56:41,425][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:56:41,935][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:56:42,444][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:56:42,954][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:56:43,463][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:56:43,974][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:56:44,483][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:56:44,992][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:56:45,501][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:56:46,011][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:56:46,521][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:56:47,033][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:56:47,542][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:56:48,050][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:56:48,559][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:56:49,069][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:56:49,579][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:56:50,088][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:56:50,597][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:56:51,105][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:56:51,616][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:56:52,125][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:56:52,636][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:56:53,147][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:56:53,657][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:56:54,165][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:56:54,675][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:56:55,184][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:56:55,693][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:56:56,202][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:56:56,711][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:56:57,220][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:56:57,729][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:56:58,237][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:56:58,746][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:56:59,254][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:56:59,764][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:57:00,274][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:57:00,782][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:57:01,292][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:57:01,801][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:57:02,311][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:57:02,821][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:57:03,330][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:57:03,840][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:57:04,349][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:57:04,857][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:57:05,367][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:57:05,876][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:57:06,385][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:57:06,910][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:57:07,419][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:57:07,927][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:57:08,436][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:57:08,946][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:57:09,455][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:57:09,964][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:57:10,473][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:57:10,982][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:57:11,490][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:57:12,000][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:57:12,509][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:57:13,018][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:57:13,527][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:57:14,037][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:57:14,546][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:57:15,057][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:57:15,566][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:57:16,076][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:57:16,584][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:57:17,094][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:57:17,603][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:57:18,113][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:57:18,623][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:57:19,132][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:57:19,642][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:57:20,152][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:57:20,660][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:57:21,168][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:57:21,677][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:57:22,185][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:57:22,693][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:57:23,202][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:57:23,713][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:57:24,223][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:57:24,732][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:57:25,241][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:57:25,751][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:57:26,261][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:57:26,770][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:57:27,279][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:57:27,788][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:57:28,296][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:57:28,804][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:57:29,315][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:57:29,824][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:57:30,333][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:57:30,842][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:57:31,351][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:57:31,860][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:57:32,369][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:57:32,878][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:57:33,387][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:57:33,895][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:57:34,404][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:57:34,914][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:57:35,424][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:57:35,933][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:57:36,442][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:57:36,953][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:57:37,462][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:57:37,971][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:57:38,480][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:57:38,989][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:57:39,498][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:57:40,007][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:57:40,517][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:57:41,029][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:57:41,538][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:57:42,048][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:57:42,558][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:57:43,067][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:57:43,575][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:57:44,085][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21758 tokens. [2026-03-26 00:57:44,772][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-26 00:57:45,529][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:57:45,531][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:57:45,533][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:57:46,435][__main__][INFO] - Iteration 431 took 1m 15s (9.05% Gen, 89.76% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 57m 21s. Estimated total time: 63h 19m 54s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 39s, 500 more iterations: 10h 33m 19s. [2026-03-26 00:57:46,437][__main__][INFO] - Starting iteration 431. [2026-03-26 00:57:46,841][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:57:46,842][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:57:47,448][mllm.models.large_language_model_local][WARNING] - Response Proposal: 0 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:57:53,969][__main__][INFO] - Number of regex retries in iteration 431: 1 [2026-03-26 00:57:53,970][__main__][INFO] - agents played in iteration 431 are Bob, Alice [2026-03-26 00:57:54,929][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:57:55,556][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:57:56,022][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:57:56,538][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:57:57,048][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:57:57,558][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:57:58,067][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:57:58,576][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:57:59,086][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:57:59,595][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:58:00,103][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:58:00,613][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:58:01,122][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:58:01,631][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:58:02,140][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:58:02,650][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:58:03,160][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:58:03,668][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:58:04,178][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:58:04,686][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:58:05,195][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:58:05,703][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:58:06,213][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:58:06,721][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:58:07,230][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:58:07,739][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:58:08,249][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:58:08,759][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:58:09,267][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:58:09,777][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:58:10,286][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:58:10,796][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:58:11,307][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:58:11,817][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:58:12,333][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:58:12,844][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:58:13,356][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:58:13,872][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:58:14,384][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:58:14,906][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:58:15,419][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:58:15,931][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:58:16,443][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:58:16,955][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:58:17,466][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:58:17,977][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:58:18,488][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:58:18,999][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:58:19,510][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:58:20,021][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:58:20,538][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:58:21,052][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:58:21,566][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:58:22,079][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:58:22,592][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:58:23,105][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:58:23,619][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:58:24,133][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:58:24,644][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:58:25,154][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:58:25,665][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:58:26,175][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:58:26,687][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:58:27,197][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:58:27,707][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:58:28,216][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:58:28,726][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:58:29,237][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:58:29,747][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:58:30,257][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:58:30,767][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:58:31,277][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:58:31,787][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:58:32,296][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:58:32,806][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:58:33,315][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:58:33,825][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:58:34,335][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:58:34,845][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:58:35,354][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:58:35,865][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:58:36,374][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:58:36,883][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:58:37,392][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:58:37,901][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:58:38,412][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:58:38,921][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:58:39,431][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:58:39,940][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:58:40,448][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:58:40,958][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:58:41,467][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:58:41,977][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:58:42,487][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:58:42,997][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 00:58:43,506][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 00:58:44,015][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 00:58:44,525][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 00:58:45,036][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 00:58:45,546][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 00:58:46,055][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 00:58:46,565][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 00:58:47,074][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 00:58:47,584][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 00:58:48,093][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 00:58:48,602][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 00:58:49,112][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 00:58:49,621][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 00:58:50,130][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 00:58:50,639][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 00:58:51,148][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 00:58:51,657][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 00:58:52,166][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 00:58:52,679][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 00:58:53,193][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 00:58:53,706][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 00:58:54,219][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 00:58:54,737][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 00:58:55,251][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 00:58:55,765][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 00:58:56,278][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 00:58:56,791][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 00:58:57,311][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 00:58:57,822][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 00:58:58,333][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 00:58:58,844][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 00:58:59,355][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 00:58:59,873][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 00:59:00,384][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 00:59:00,896][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-26 00:59:01,583][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.53%, ΔTime: 00:01:06 [2026-03-26 00:59:02,332][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 00:59:02,335][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 00:59:02,336][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 00:59:03,155][__main__][INFO] - Iteration 432 took 1m 16s (9.34% Gen, 89.59% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 11m 53s. Estimated total time: 63h 35m 43s. Time estimates for 10 more iterations: 12m 43s, 100 more iterations: 2h 7m 11s, 500 more iterations: 10h 35m 57s. [2026-03-26 00:59:03,157][__main__][INFO] - Starting iteration 432. [2026-03-26 00:59:03,558][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 00:59:03,559][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 00:59:05,339][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 00:59:10,319][__main__][INFO] - Number of regex retries in iteration 432: 1 [2026-03-26 00:59:10,321][__main__][INFO] - agents played in iteration 432 are Bob, Alice [2026-03-26 00:59:11,284][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 00:59:12,202][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 00:59:12,666][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 00:59:13,180][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 00:59:13,690][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 00:59:14,201][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 00:59:14,710][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 00:59:15,219][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 00:59:15,728][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 00:59:16,238][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 00:59:16,747][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 00:59:17,256][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 00:59:17,766][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 00:59:18,275][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 00:59:18,783][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 00:59:19,293][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 00:59:19,802][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 00:59:20,311][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 00:59:20,821][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 00:59:21,331][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 00:59:21,841][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 00:59:22,350][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 00:59:22,859][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 00:59:23,368][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 00:59:23,877][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 00:59:24,386][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 00:59:24,898][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 00:59:25,408][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 00:59:25,918][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 00:59:26,429][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 00:59:26,940][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 00:59:27,451][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 00:59:27,961][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 00:59:28,472][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 00:59:28,981][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 00:59:29,490][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 00:59:30,000][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 00:59:30,510][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 00:59:31,019][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 00:59:31,528][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 00:59:32,037][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 00:59:32,547][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 00:59:33,057][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 00:59:33,570][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 00:59:34,080][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 00:59:34,591][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 00:59:35,101][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 00:59:35,611][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 00:59:36,120][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 00:59:36,632][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 00:59:37,142][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 00:59:37,650][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 00:59:38,159][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 00:59:38,667][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 00:59:39,177][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 00:59:39,684][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 00:59:40,192][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 00:59:40,701][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 00:59:41,212][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 00:59:41,721][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 00:59:42,232][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 00:59:42,742][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 00:59:43,252][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 00:59:43,762][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 00:59:44,273][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 00:59:44,782][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 00:59:45,290][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 00:59:45,799][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 00:59:46,307][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 00:59:46,816][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 00:59:47,325][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 00:59:47,833][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 00:59:48,341][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 00:59:48,851][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 00:59:49,359][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 00:59:49,868][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 00:59:50,377][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 00:59:50,885][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 00:59:51,394][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 00:59:51,902][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 00:59:52,412][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 00:59:52,921][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 00:59:53,430][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 00:59:53,939][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 00:59:54,449][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 00:59:54,957][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 00:59:55,466][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 00:59:55,975][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 00:59:56,484][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 00:59:56,993][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 00:59:57,501][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 00:59:58,013][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 00:59:58,522][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 00:59:59,034][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 00:59:59,545][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:00:00,056][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:00:00,565][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:00:01,077][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:00:01,587][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:00:02,097][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:00:02,607][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:00:03,117][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:00:03,626][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:00:04,137][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:00:04,645][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:00:05,155][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:00:05,665][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:00:06,173][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:00:06,683][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:00:07,193][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:00:07,702][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:00:08,213][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:00:08,723][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:00:09,233][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:00:09,742][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:00:10,252][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:00:10,762][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:00:11,272][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:00:11,782][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:00:12,292][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:00:12,804][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:00:13,315][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:00:13,826][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:00:14,338][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:00:14,848][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:00:15,359][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:00:15,870][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:00:16,381][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:00:16,898][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:00:17,410][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 01:00:18,087][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 01:00:18,833][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:00:18,836][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:00:18,837][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:00:19,541][__main__][INFO] - Iteration 433 took 1m 15s (8.90% Gen, 90.17% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 54m 5s. Estimated total time: 63h 19m 11s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 38s, 500 more iterations: 10h 33m 11s. [2026-03-26 01:00:19,543][__main__][INFO] - Starting iteration 433. [2026-03-26 01:00:19,947][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:00:19,948][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:00:27,143][__main__][INFO] - Number of regex retries in iteration 433: 0 [2026-03-26 01:00:27,144][__main__][INFO] - agents played in iteration 433 are Bob, Alice [2026-03-26 01:00:28,104][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:00:28,743][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:00:29,209][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:00:29,725][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:00:30,235][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:00:30,745][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:00:31,255][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:00:31,765][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:00:32,275][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:00:32,785][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:00:33,295][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:00:33,804][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:00:34,314][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:00:34,824][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:00:35,333][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:00:35,843][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:00:36,354][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:00:36,864][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:00:37,373][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:00:37,882][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:00:38,393][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:00:38,903][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:00:39,411][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:00:39,920][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:00:40,431][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:00:40,940][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:00:41,452][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:00:41,962][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:00:42,473][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:00:42,982][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:00:43,494][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:00:44,005][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:00:44,516][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:00:45,026][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:00:45,536][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:00:46,045][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:00:46,554][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:00:47,063][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:00:47,572][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:00:48,081][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:00:48,591][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:00:49,099][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:00:49,608][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:00:50,118][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:00:50,627][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:00:51,136][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:00:51,645][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:00:52,154][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:00:52,663][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:00:53,173][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:00:53,683][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:00:54,192][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:00:54,701][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:00:55,210][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:00:55,718][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:00:56,227][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:00:56,736][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:00:57,246][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:00:57,755][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:00:58,264][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:00:58,774][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:00:59,283][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:00:59,793][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:01:00,303][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:01:00,812][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:01:01,322][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:01:01,833][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:01:02,343][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:01:02,852][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:01:03,362][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:01:03,872][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:01:04,381][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:01:04,890][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:01:05,400][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:01:05,909][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:01:06,417][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:01:06,926][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:01:07,436][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:01:07,946][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:01:08,455][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:01:08,964][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:01:09,474][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:01:09,983][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:01:10,492][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:01:11,000][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:01:11,508][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:01:12,016][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:01:12,525][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:01:13,034][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:01:13,544][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:01:14,053][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:01:14,563][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:01:15,074][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:01:15,584][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:01:16,095][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:01:16,605][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:01:17,115][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:01:17,625][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:01:18,134][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:01:18,643][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:01:19,153][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:01:19,662][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:01:20,170][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:01:20,679][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:01:21,187][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:01:21,696][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:01:22,205][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:01:22,714][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:01:23,224][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:01:23,736][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:01:24,245][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:01:24,755][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:01:25,265][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:01:25,774][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:01:26,283][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:01:26,791][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:01:27,299][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:01:27,807][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:01:28,316][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:01:28,825][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:01:29,334][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:01:29,843][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:01:30,352][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:01:30,861][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:01:31,370][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:01:31,880][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:01:32,389][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:01:32,897][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:01:33,406][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:01:33,915][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-26 01:01:34,582][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-26 01:01:35,345][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:01:35,347][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:01:35,349][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:01:36,242][__main__][INFO] - Iteration 434 took 1m 16s (9.43% Gen, 89.40% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 8m 24s. Estimated total time: 63h 34m 47s. Time estimates for 10 more iterations: 12m 42s, 100 more iterations: 2h 7m 9s, 500 more iterations: 10h 35m 47s. [2026-03-26 01:01:36,244][__main__][INFO] - Starting iteration 434. [2026-03-26 01:01:36,645][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:01:36,646][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:01:37,274][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:01:37,279][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:01:43,824][__main__][INFO] - Number of regex retries in iteration 434: 2 [2026-03-26 01:01:43,825][__main__][INFO] - agents played in iteration 434 are Bob, Alice [2026-03-26 01:01:44,795][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:01:45,431][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:01:45,898][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:01:46,414][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:01:46,924][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:01:47,436][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:01:47,946][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:01:48,457][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:01:48,971][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:01:49,482][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:01:49,995][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:01:50,507][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:01:51,019][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:01:51,530][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:01:52,042][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:01:52,553][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:01:53,071][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:01:53,584][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:01:54,096][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:01:54,607][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:01:55,118][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:01:55,630][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:01:56,141][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:01:56,654][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:01:57,176][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:01:57,688][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:01:58,198][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:01:58,707][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:01:59,217][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:01:59,726][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:02:00,235][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:02:00,745][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:02:01,254][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:02:01,767][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:02:02,279][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:02:02,789][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:02:03,301][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:02:03,812][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:02:04,323][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:02:04,836][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:02:05,347][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:02:05,858][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:02:06,368][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:02:06,878][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:02:07,388][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:02:07,897][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:02:08,408][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:02:08,918][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:02:09,428][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:02:09,939][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:02:10,449][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:02:10,959][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:02:11,468][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:02:11,978][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:02:12,487][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:02:12,997][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:02:13,506][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:02:14,016][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:02:14,526][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:02:15,037][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:02:15,547][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:02:16,058][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:02:16,568][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:02:17,077][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:02:17,587][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:02:18,097][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:02:18,606][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:02:19,117][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:02:19,627][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:02:20,137][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:02:20,647][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:02:21,156][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:02:21,666][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:02:22,176][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:02:22,685][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:02:23,195][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:02:23,704][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:02:24,214][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:02:24,723][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:02:25,232][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:02:25,742][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:02:26,253][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:02:26,763][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:02:27,271][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:02:27,780][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:02:28,290][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:02:28,799][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:02:29,308][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:02:29,817][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:02:30,326][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:02:30,832][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:02:31,340][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:02:31,847][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:02:32,355][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:02:32,863][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:02:33,370][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:02:33,877][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:02:34,384][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:02:34,894][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:02:35,402][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:02:35,915][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:02:36,425][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:02:36,936][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:02:37,444][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:02:37,954][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:02:38,463][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:02:38,973][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:02:39,482][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:02:39,992][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:02:40,502][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:02:41,012][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:02:41,521][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:02:42,031][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:02:42,540][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:02:43,049][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:02:43,557][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:02:44,066][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:02:44,576][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:02:45,084][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:02:45,593][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:02:46,102][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:02:46,611][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:02:47,122][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:02:47,633][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:02:48,142][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:02:48,652][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:02:49,162][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:02:49,671][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:02:50,181][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:02:50,690][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-26 01:02:51,358][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:05 [2026-03-26 01:02:52,105][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:02:52,107][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:02:52,109][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:02:52,860][__main__][INFO] - Iteration 435 took 1m 16s (9.42% Gen, 89.59% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 3m 8s. Estimated total time: 63h 30m 47s. Time estimates for 10 more iterations: 12m 42s, 100 more iterations: 2h 7m 1s, 500 more iterations: 10h 35m 7s. [2026-03-26 01:02:52,862][__main__][INFO] - Starting iteration 435. [2026-03-26 01:02:53,264][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:02:53,265][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:02:55,479][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:02:59,633][__main__][INFO] - Number of regex retries in iteration 435: 1 [2026-03-26 01:02:59,634][__main__][INFO] - agents played in iteration 435 are Bob, Alice [2026-03-26 01:03:00,590][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:03:01,516][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:03:01,983][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:03:02,499][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:03:03,010][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:03:03,520][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:03:04,038][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:03:04,551][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:03:05,064][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:03:05,576][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:03:06,087][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:03:06,598][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:03:07,108][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:03:07,619][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:03:08,134][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:03:08,646][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:03:09,158][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:03:09,670][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:03:10,181][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:03:10,692][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:03:11,203][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:03:11,715][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:03:12,234][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:03:12,748][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:03:13,260][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:03:13,771][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:03:14,285][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:03:14,797][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:03:15,309][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:03:15,821][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:03:16,342][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:03:16,855][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:03:17,367][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:03:17,879][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:03:18,391][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:03:18,901][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:03:19,413][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:03:19,923][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:03:20,439][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:03:20,950][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:03:21,461][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:03:21,971][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:03:22,480][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:03:22,989][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:03:23,498][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:03:24,008][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:03:24,518][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:03:25,026][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:03:25,536][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:03:26,046][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:03:26,555][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:03:27,064][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:03:27,571][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:03:28,080][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:03:28,587][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:03:29,095][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:03:29,604][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:03:30,114][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:03:30,623][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:03:31,134][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:03:31,643][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:03:32,153][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:03:32,662][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:03:33,171][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:03:33,681][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:03:34,191][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:03:34,701][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:03:35,212][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:03:35,722][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:03:36,233][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:03:36,743][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:03:37,254][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:03:37,764][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:03:38,273][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:03:38,782][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:03:39,291][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:03:39,800][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:03:40,309][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:03:40,818][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:03:41,326][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:03:41,836][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:03:42,346][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:03:42,856][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:03:43,364][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:03:43,873][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:03:44,383][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:03:44,892][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:03:45,400][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:03:45,909][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:03:46,417][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:03:46,926][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:03:47,436][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:03:47,946][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:03:48,456][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:03:48,965][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:03:49,475][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:03:49,983][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:03:50,492][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:03:51,001][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:03:51,511][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:03:52,021][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:03:52,531][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:03:53,042][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:03:53,555][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:03:54,064][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:03:54,575][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:03:55,083][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:03:55,592][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:03:56,101][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:03:56,611][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:03:57,121][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:03:57,631][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:03:58,141][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:03:58,653][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:03:59,163][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:03:59,671][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:04:00,180][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:04:00,689][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:04:01,198][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:04:01,706][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:04:02,215][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:04:02,723][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:04:03,233][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:04:03,744][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:04:04,254][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:04:04,765][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:04:05,274][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:04:05,783][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:04:06,292][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:04:06,802][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-26 01:04:07,468][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-26 01:04:08,247][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:04:08,250][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:04:08,252][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:04:08,978][__main__][INFO] - Iteration 436 took 1m 15s (8.41% Gen, 90.63% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 36m 48s. Estimated total time: 63h 5m 44s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 11s, 500 more iterations: 10h 30m 57s. [2026-03-26 01:04:08,980][__main__][INFO] - Starting iteration 436. [2026-03-26 01:04:09,381][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:04:09,382][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:04:14,712][mllm.models.large_language_model_local][WARNING] - Response Given the current values, you should focus on getting as many balls as possible since they have the highest value for you. Here's a strategic proposal: Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:04:16,912][__main__][INFO] - Number of regex retries in iteration 436: 1 [2026-03-26 01:04:16,913][__main__][INFO] - agents played in iteration 436 are Bob, Alice [2026-03-26 01:04:17,865][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:04:18,493][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:04:18,961][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:04:19,476][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:04:19,987][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:04:20,498][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:04:21,009][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:04:21,520][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:04:22,031][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:04:22,543][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:04:23,052][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:04:23,563][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:04:24,073][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:04:24,582][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:04:25,091][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:04:25,601][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:04:26,111][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:04:26,620][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:04:27,129][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:04:27,640][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:04:28,149][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:04:28,657][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:04:29,167][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:04:29,676][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:04:30,185][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:04:30,694][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:04:31,202][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:04:31,713][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:04:32,222][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:04:32,733][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:04:33,243][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:04:33,752][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:04:34,261][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:04:34,770][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:04:35,279][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:04:35,788][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:04:36,296][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:04:36,806][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:04:37,316][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:04:37,825][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:04:38,337][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:04:38,846][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:04:39,355][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:04:39,863][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:04:40,370][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:04:40,879][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:04:41,389][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:04:41,898][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:04:42,409][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:04:42,920][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:04:43,429][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:04:43,938][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:04:44,447][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:04:44,956][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:04:45,465][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:04:45,975][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:04:46,484][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:04:46,995][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:04:47,504][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:04:48,014][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:04:48,523][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:04:49,034][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:04:49,543][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:04:50,054][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:04:50,564][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:04:51,073][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:04:51,585][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:04:52,095][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:04:52,605][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:04:53,118][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:04:53,629][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:04:54,140][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:04:54,652][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:04:55,164][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:04:55,673][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:04:56,183][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:04:56,693][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:04:57,202][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:04:57,711][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:04:58,221][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:04:58,732][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:04:59,243][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:04:59,752][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:05:00,261][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:05:00,771][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:05:01,280][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:05:01,788][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:05:02,298][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:05:02,807][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:05:03,317][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:05:03,826][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:05:04,335][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:05:04,846][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:05:05,355][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:05:05,865][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:05:06,372][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:05:06,881][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:05:07,391][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:05:07,902][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:05:08,411][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:05:08,920][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:05:09,429][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:05:09,938][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:05:10,447][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:05:10,956][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:05:11,466][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:05:11,975][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:05:12,483][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:05:12,990][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:05:13,500][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:05:14,008][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:05:14,517][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:05:15,026][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:05:15,535][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:05:16,045][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:05:16,555][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:05:17,065][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:05:17,575][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:05:18,084][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:05:18,594][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:05:19,103][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:05:19,613][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:05:20,122][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:05:20,633][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:05:21,141][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:05:21,649][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:05:22,157][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:05:22,665][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:05:23,173][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:05:23,682][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21749 tokens. [2026-03-26 01:05:24,327][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 01:05:25,070][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:05:25,073][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:05:25,074][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:05:25,738][__main__][INFO] - Iteration 437 took 1m 16s (9.86% Gen, 89.27% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 7m 41s. Estimated total time: 63h 37m 53s. Time estimates for 10 more iterations: 12m 43s, 100 more iterations: 2h 7m 15s, 500 more iterations: 10h 36m 18s. [2026-03-26 01:05:25,740][__main__][INFO] - Starting iteration 437. [2026-03-26 01:05:26,141][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:05:26,142][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:05:32,497][__main__][INFO] - Number of regex retries in iteration 437: 0 [2026-03-26 01:05:32,789][__main__][INFO] - agents played in iteration 437 are Bob, Alice [2026-03-26 01:05:33,763][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:05:34,381][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:05:34,846][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:05:35,360][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:05:35,868][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:05:36,377][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:05:36,886][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:05:37,394][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:05:37,902][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:05:38,411][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:05:38,922][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:05:39,432][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:05:39,943][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:05:40,453][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:05:40,962][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:05:41,472][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:05:41,981][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:05:42,491][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:05:42,999][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:05:43,508][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:05:44,017][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:05:44,526][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:05:45,034][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:05:45,544][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:05:46,053][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:05:46,563][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:05:47,074][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:05:47,583][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:05:48,094][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:05:48,604][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:05:49,116][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:05:49,627][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:05:50,137][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:05:50,647][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:05:51,157][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:05:51,666][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:05:52,176][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:05:52,685][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:05:53,194][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:05:53,704][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:05:54,213][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:05:54,723][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:05:55,233][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:05:55,741][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:05:56,250][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:05:56,758][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:05:57,267][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:05:57,775][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:05:58,284][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:05:58,793][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:05:59,302][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:05:59,812][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:06:00,321][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:06:00,832][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:06:01,342][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:06:01,854][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:06:02,366][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:06:02,876][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:06:03,385][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:06:03,894][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:06:04,403][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:06:04,914][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:06:05,423][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:06:05,933][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:06:06,444][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:06:06,955][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:06:07,465][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:06:07,974][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:06:08,483][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:06:08,993][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:06:09,503][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:06:10,012][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:06:10,521][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:06:11,033][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:06:11,545][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:06:12,055][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:06:12,566][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:06:13,077][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:06:13,588][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:06:14,098][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:06:14,608][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:06:15,119][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:06:15,628][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:06:16,137][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:06:16,646][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:06:17,154][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:06:17,663][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:06:18,173][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:06:18,681][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:06:19,189][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:06:19,700][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:06:20,211][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:06:20,722][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:06:21,236][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:06:21,748][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:06:22,260][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:06:22,770][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:06:23,283][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:06:23,793][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:06:24,302][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:06:24,815][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:06:25,326][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:06:25,837][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:06:26,348][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:06:26,858][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:06:27,368][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:06:27,878][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:06:28,386][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:06:28,895][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:06:29,404][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:06:29,913][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:06:30,422][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:06:30,931][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:06:31,439][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:06:31,950][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:06:32,460][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:06:32,969][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:06:33,479][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:06:33,988][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:06:34,497][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:06:35,007][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:06:35,517][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:06:36,026][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:06:36,535][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:06:37,044][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:06:37,555][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:06:38,065][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:06:38,575][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:06:39,083][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:06:39,593][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21749 tokens. [2026-03-26 01:06:40,256][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:05 [2026-03-26 01:06:40,998][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:06:41,000][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:06:41,002][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:06:41,717][__main__][INFO] - Iteration 438 took 1m 15s (8.80% Gen, 90.26% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 27m 22s. Estimated total time: 62h 58m 50s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 57s, 500 more iterations: 10h 29m 48s. [2026-03-26 01:06:41,719][__main__][INFO] - Starting iteration 438. [2026-03-26 01:06:42,124][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:06:42,125][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:06:49,067][__main__][INFO] - Number of regex retries in iteration 438: 0 [2026-03-26 01:06:49,068][__main__][INFO] - agents played in iteration 438 are Bob, Alice [2026-03-26 01:06:50,084][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:06:50,703][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:06:51,169][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:06:51,683][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:06:52,193][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:06:52,701][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:06:53,211][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:06:53,720][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:06:54,230][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:06:54,739][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:06:55,246][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:06:55,755][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:06:56,264][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:06:56,773][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:06:57,281][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:06:57,789][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:06:58,297][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:06:58,806][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:06:59,316][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:06:59,823][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:07:00,332][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:07:00,841][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:07:01,350][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:07:01,859][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:07:02,367][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:07:02,875][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:07:03,385][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:07:03,895][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:07:04,404][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:07:04,914][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:07:05,422][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:07:05,932][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:07:06,442][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:07:06,954][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:07:07,465][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:07:07,975][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:07:08,485][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:07:08,995][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:07:09,505][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:07:10,016][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:07:10,525][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:07:11,035][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:07:11,543][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:07:12,051][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:07:12,560][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:07:13,069][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:07:13,577][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:07:14,085][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:07:14,594][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:07:15,104][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:07:15,613][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:07:16,121][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:07:16,630][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:07:17,138][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:07:17,647][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:07:18,157][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:07:18,666][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:07:19,174][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:07:19,683][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:07:20,192][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:07:20,702][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:07:21,212][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:07:21,720][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:07:22,229][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:07:22,739][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:07:23,247][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:07:23,757][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:07:24,266][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:07:24,775][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:07:25,284][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:07:25,794][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:07:26,303][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:07:26,813][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:07:27,323][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:07:27,832][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:07:28,340][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:07:28,848][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:07:29,357][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:07:29,866][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:07:30,374][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:07:30,882][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:07:31,390][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:07:31,899][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:07:32,408][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:07:32,916][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:07:33,425][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:07:33,935][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:07:34,443][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:07:34,953][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:07:35,463][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:07:35,972][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:07:36,481][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:07:36,990][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:07:37,500][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:07:38,009][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:07:38,518][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:07:39,027][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:07:39,536][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:07:40,046][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:07:40,556][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:07:41,067][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:07:41,575][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:07:42,085][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:07:42,595][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:07:43,105][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:07:43,616][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:07:44,125][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:07:44,634][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:07:45,143][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:07:45,651][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:07:46,160][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:07:46,669][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:07:47,178][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:07:47,687][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:07:48,196][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:07:48,705][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:07:49,216][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:07:49,726][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:07:50,236][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:07:50,746][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:07:51,255][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:07:51,763][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:07:52,273][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:07:52,782][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:07:53,294][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:07:53,805][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:07:54,315][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:07:54,824][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:07:55,335][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:07:55,845][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-26 01:07:56,507][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:05 [2026-03-26 01:07:57,262][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:07:57,264][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:07:57,266][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:07:57,937][__main__][INFO] - Iteration 439 took 1m 15s (9.16% Gen, 89.95% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 37m 56s. Estimated total time: 63h 10m 41s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 21s, 500 more iterations: 10h 31m 46s. [2026-03-26 01:07:57,940][__main__][INFO] - Starting iteration 439. [2026-03-26 01:07:58,342][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:07:58,343][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:07:58,975][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:08:05,031][__main__][INFO] - Number of regex retries in iteration 439: 1 [2026-03-26 01:08:05,032][__main__][INFO] - agents played in iteration 439 are Bob, Alice [2026-03-26 01:08:06,006][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:08:06,645][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:08:07,112][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:08:07,629][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:08:08,141][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:08:08,654][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:08:09,163][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:08:09,674][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:08:10,185][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:08:10,696][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:08:11,205][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:08:11,714][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:08:12,223][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:08:12,734][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:08:13,244][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:08:13,754][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:08:14,263][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:08:14,772][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:08:15,283][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:08:15,793][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:08:16,302][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:08:16,815][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:08:17,326][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:08:17,837][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:08:18,347][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:08:18,857][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:08:19,368][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:08:19,879][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:08:20,389][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:08:20,900][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:08:21,410][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:08:21,921][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:08:22,433][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:08:22,944][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:08:23,454][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:08:23,964][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:08:24,474][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:08:24,984][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:08:25,495][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:08:26,006][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:08:26,516][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:08:27,026][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:08:27,537][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:08:28,046][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:08:28,558][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:08:29,068][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:08:29,577][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:08:30,088][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:08:30,598][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:08:31,109][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:08:31,619][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:08:32,127][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:08:32,638][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:08:33,149][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:08:33,657][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:08:34,166][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:08:34,675][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:08:35,184][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:08:35,694][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:08:36,203][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:08:36,712][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:08:37,223][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:08:37,733][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:08:38,244][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:08:38,754][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:08:39,264][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:08:39,775][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:08:40,287][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:08:40,797][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:08:41,309][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:08:41,820][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:08:42,330][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:08:42,841][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:08:43,353][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:08:43,864][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:08:44,374][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:08:44,884][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:08:45,393][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:08:45,903][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:08:46,413][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:08:46,923][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:08:47,432][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:08:47,943][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:08:48,455][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:08:48,965][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:08:49,475][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:08:49,984][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:08:50,494][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:08:51,003][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:08:51,513][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:08:52,023][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:08:52,534][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:08:53,045][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:08:53,556][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:08:54,066][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:08:54,575][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:08:55,086][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:08:55,597][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:08:56,105][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:08:56,615][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:08:57,123][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:08:57,632][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:08:58,142][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:08:58,651][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:08:59,159][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:08:59,668][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:09:00,177][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:09:00,687][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:09:01,197][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:09:01,707][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:09:02,217][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:09:02,727][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:09:03,237][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:09:03,747][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:09:04,256][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:09:04,766][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:09:05,275][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:09:05,783][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:09:06,293][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:09:06,803][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:09:07,312][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:09:07,821][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:09:08,331][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:09:08,841][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:09:09,351][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:09:09,863][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:09:10,373][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:09:10,883][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:09:11,392][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:09:11,901][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21748 tokens. [2026-03-26 01:09:12,560][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:05 [2026-03-26 01:09:13,313][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:09:13,316][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:09:13,317][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:09:13,990][__main__][INFO] - Iteration 440 took 1m 15s (8.84% Gen, 90.27% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 28m 24s. Estimated total time: 63h 2m 24s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 4s, 500 more iterations: 10h 30m 24s. [2026-03-26 01:09:13,992][__main__][INFO] - Starting iteration 440. [2026-03-26 01:09:14,394][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:09:14,395][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:09:21,946][__main__][INFO] - Number of regex retries in iteration 440: 0 [2026-03-26 01:09:21,947][__main__][INFO] - agents played in iteration 440 are Bob, Alice [2026-03-26 01:09:22,932][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:09:23,565][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:09:24,030][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:09:24,545][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:09:25,054][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:09:25,564][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:09:26,072][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:09:26,581][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:09:27,091][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:09:27,600][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:09:28,109][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:09:28,618][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:09:29,126][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:09:29,635][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:09:30,146][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:09:30,655][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:09:31,163][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:09:31,672][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:09:32,181][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:09:32,690][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:09:33,198][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:09:33,707][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:09:34,216][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:09:34,725][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:09:35,235][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:09:35,745][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:09:36,256][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:09:36,766][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:09:37,275][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:09:37,784][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:09:38,295][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:09:38,804][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:09:39,313][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:09:39,823][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:09:40,332][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:09:40,840][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:09:41,349][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:09:41,858][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:09:42,366][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:09:42,875][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:09:43,384][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:09:43,894][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:09:44,408][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:09:44,920][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:09:45,434][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:09:45,947][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:09:46,458][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:09:46,968][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:09:47,480][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:09:47,992][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:09:48,501][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:09:49,010][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:09:49,519][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:09:50,028][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:09:50,537][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:09:51,045][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:09:51,555][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:09:52,063][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:09:52,573][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:09:53,082][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:09:53,591][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:09:54,100][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:09:54,609][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:09:55,117][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:09:55,626][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:09:56,135][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:09:56,644][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:09:57,153][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:09:57,662][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:09:58,171][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:09:58,680][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:09:59,189][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:09:59,697][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:10:00,206][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:10:00,715][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:10:01,224][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:10:01,733][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:10:02,242][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:10:02,751][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:10:03,259][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:10:03,767][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:10:04,275][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:10:04,784][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:10:05,292][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:10:05,800][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:10:06,309][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:10:06,819][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:10:07,326][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:10:07,837][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:10:08,347][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:10:08,855][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:10:09,364][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:10:09,873][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:10:10,382][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:10:10,891][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:10:11,400][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:10:11,910][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:10:12,418][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:10:12,926][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:10:13,436][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:10:13,945][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:10:14,454][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:10:14,964][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:10:15,473][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:10:15,981][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:10:16,489][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:10:17,001][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:10:17,513][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:10:18,026][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:10:18,539][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:10:19,050][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:10:19,563][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:10:20,074][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:10:20,586][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:10:21,095][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:10:21,603][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:10:22,115][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:10:22,624][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:10:23,133][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:10:23,643][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:10:24,153][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:10:24,662][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:10:25,172][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:10:25,681][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:10:26,190][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:10:26,699][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:10:27,208][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:10:27,717][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:10:28,226][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:10:28,736][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21735 tokens. [2026-03-26 01:10:29,405][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:05 [2026-03-26 01:10:30,148][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:10:30,150][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:10:30,152][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:10:30,815][__main__][INFO] - Iteration 441 took 1m 16s (9.88% Gen, 89.25% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 5m 48s. Estimated total time: 63h 41m 6s. Time estimates for 10 more iterations: 12m 44s, 100 more iterations: 2h 7m 22s, 500 more iterations: 10h 36m 51s. [2026-03-26 01:10:30,818][__main__][INFO] - Starting iteration 441. [2026-03-26 01:10:31,224][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:10:31,224][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:10:38,209][__main__][INFO] - Number of regex retries in iteration 441: 0 [2026-03-26 01:10:38,210][__main__][INFO] - agents played in iteration 441 are Bob, Alice [2026-03-26 01:10:39,189][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:10:39,825][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:10:40,288][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:10:40,801][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:10:41,309][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:10:41,818][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:10:42,326][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:10:42,837][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:10:43,346][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:10:43,854][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:10:44,365][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:10:44,874][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:10:45,383][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:10:45,892][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:10:46,400][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:10:46,908][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:10:47,417][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:10:47,925][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:10:48,436][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:10:48,945][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:10:49,452][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:10:49,963][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:10:50,473][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:10:50,981][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:10:51,489][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:10:51,998][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:10:52,506][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:10:53,013][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:10:53,522][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:10:54,033][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:10:54,542][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:10:55,050][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:10:55,559][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:10:56,068][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:10:56,580][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:10:57,090][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:10:57,600][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:10:58,108][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:10:58,619][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:10:59,129][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:10:59,639][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:11:00,149][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:11:00,658][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:11:01,167][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:11:01,677][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:11:02,186][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:11:02,695][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:11:03,205][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:11:03,715][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:11:04,225][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:11:04,736][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:11:05,245][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:11:05,755][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:11:06,265][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:11:06,775][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:11:07,285][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:11:07,794][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:11:08,302][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:11:08,814][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:11:09,324][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:11:09,835][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:11:10,344][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:11:10,855][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:11:11,364][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:11:11,873][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:11:12,383][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:11:12,891][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:11:13,399][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:11:13,907][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:11:14,416][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:11:14,925][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:11:15,434][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:11:15,943][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:11:16,453][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:11:16,962][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:11:17,471][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:11:17,980][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:11:18,489][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:11:18,998][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:11:19,505][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:11:20,015][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:11:20,523][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:11:21,033][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:11:21,542][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:11:22,053][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:11:22,563][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:11:23,071][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:11:23,580][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:11:24,090][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:11:24,599][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:11:25,106][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:11:25,615][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:11:26,123][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:11:26,632][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:11:27,141][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:11:27,650][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:11:28,158][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:11:28,666][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:11:29,177][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:11:29,686][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:11:30,196][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:11:30,705][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:11:31,215][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:11:31,724][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:11:32,235][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:11:32,745][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:11:33,255][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:11:33,765][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:11:34,275][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:11:34,784][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:11:35,293][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:11:35,802][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:11:36,313][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:11:36,824][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:11:37,333][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:11:37,842][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:11:38,353][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:11:38,863][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:11:39,372][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:11:39,881][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:11:40,390][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:11:40,898][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:11:41,407][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:11:41,917][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:11:42,426][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:11:42,936][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:11:43,445][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:11:43,955][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:11:44,465][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:11:44,974][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-26 01:11:45,636][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.20%, ΔTime: 00:01:05 [2026-03-26 01:11:46,379][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:11:46,381][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:11:46,383][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:11:47,043][__main__][INFO] - Iteration 442 took 1m 15s (9.21% Gen, 89.91% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 34m 27s. Estimated total time: 63h 11m 1s. Time estimates for 10 more iterations: 12m 38s, 100 more iterations: 2h 6m 22s, 500 more iterations: 10h 31m 50s. [2026-03-26 01:11:47,045][__main__][INFO] - Starting iteration 442. [2026-03-26 01:11:47,449][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:11:47,449][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:11:48,080][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:11:54,554][__main__][INFO] - Number of regex retries in iteration 442: 1 [2026-03-26 01:11:54,555][__main__][INFO] - agents played in iteration 442 are Bob, Alice [2026-03-26 01:11:55,513][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:11:56,136][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:11:56,602][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:11:57,116][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:11:57,624][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:11:58,135][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:11:58,645][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:11:59,154][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:11:59,664][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:12:00,172][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:12:00,681][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:12:01,189][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:12:01,698][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:12:02,206][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:12:02,715][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:12:03,224][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:12:03,734][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:12:04,244][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:12:04,754][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:12:05,263][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:12:05,770][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:12:06,280][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:12:06,788][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:12:07,297][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:12:07,804][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:12:08,313][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:12:08,825][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:12:09,336][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:12:09,846][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:12:10,356][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:12:10,866][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:12:11,375][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:12:11,885][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:12:12,395][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:12:12,903][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:12:13,414][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:12:13,924][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:12:14,433][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:12:14,943][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:12:15,453][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:12:15,963][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:12:16,473][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:12:16,983][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:12:17,492][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:12:18,002][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:12:18,513][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:12:19,022][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:12:19,531][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:12:20,041][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:12:20,551][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:12:21,060][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:12:21,569][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:12:22,079][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:12:22,588][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:12:23,097][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:12:23,607][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:12:24,115][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:12:24,624][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:12:25,133][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:12:25,642][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:12:26,152][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:12:26,660][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:12:27,169][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:12:27,678][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:12:28,187][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:12:28,695][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:12:29,205][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:12:29,714][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:12:30,224][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:12:30,735][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:12:31,244][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:12:31,754][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:12:32,264][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:12:32,772][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:12:33,281][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:12:33,789][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:12:34,298][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:12:34,806][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:12:35,315][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:12:35,825][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:12:36,334][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:12:36,843][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:12:37,352][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:12:37,860][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:12:38,368][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:12:38,877][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:12:39,385][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:12:39,894][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:12:40,402][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:12:40,910][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:12:41,420][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:12:41,929][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:12:42,439][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:12:42,950][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:12:43,459][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:12:43,968][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:12:44,478][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:12:44,988][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:12:45,497][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:12:46,006][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:12:46,515][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:12:47,024][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:12:47,533][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:12:48,042][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:12:48,553][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:12:49,062][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:12:49,571][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:12:50,080][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:12:50,589][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:12:51,098][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:12:51,607][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:12:52,115][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:12:52,624][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:12:53,135][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:12:53,645][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:12:54,155][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:12:54,666][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:12:55,175][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:12:55,685][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:12:56,195][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:12:56,706][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:12:57,217][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:12:57,726][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:12:58,236][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:12:58,747][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:12:59,257][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:12:59,767][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:13:00,277][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:13:00,786][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:13:01,296][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 01:13:01,958][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-26 01:13:02,706][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:13:02,708][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:13:02,710][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:13:03,380][__main__][INFO] - Iteration 443 took 1m 15s (9.36% Gen, 89.76% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 53h 38m 47s. Estimated total time: 63h 16m 37s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 33s, 500 more iterations: 10h 32m 46s. [2026-03-26 01:13:03,383][__main__][INFO] - Starting iteration 443. [2026-03-26 01:13:03,784][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:13:03,785][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:13:11,228][__main__][INFO] - Number of regex retries in iteration 443: 0 [2026-03-26 01:13:11,229][__main__][INFO] - agents played in iteration 443 are Bob, Alice [2026-03-26 01:13:12,199][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:13:12,831][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:13:13,299][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:13:13,814][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:13:14,324][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:13:14,835][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:13:15,345][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:13:15,857][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:13:16,367][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:13:16,878][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:13:17,391][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:13:17,901][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:13:18,411][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:13:18,921][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:13:19,433][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:13:19,941][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:13:20,450][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:13:20,960][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:13:21,469][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:13:21,976][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:13:22,484][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:13:22,994][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:13:23,504][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:13:24,012][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:13:24,520][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:13:25,030][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:13:25,538][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:13:26,046][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:13:26,555][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:13:27,063][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:13:27,572][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:13:28,080][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:13:28,588][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:13:29,096][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:13:29,605][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:13:30,114][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:13:30,624][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:13:31,134][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:13:31,642][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:13:32,149][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:13:32,659][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:13:33,169][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:13:33,677][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:13:34,187][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:13:34,695][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:13:35,205][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:13:35,715][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:13:36,224][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:13:36,733][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:13:37,243][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:13:37,751][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:13:38,259][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:13:38,766][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:13:39,273][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:13:39,780][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:13:40,287][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:13:40,795][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:13:41,303][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:13:41,812][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:13:42,320][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:13:42,830][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:13:43,340][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:13:43,849][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:13:44,358][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:13:44,869][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:13:45,378][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:13:45,887][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:13:46,396][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:13:46,905][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:13:47,414][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:13:47,924][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:13:48,434][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:13:48,943][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:13:49,454][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:13:49,963][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:13:50,472][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:13:50,980][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:13:51,488][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:13:51,997][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:13:52,506][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:13:53,015][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:13:53,522][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:13:54,030][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:13:54,538][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:13:55,045][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:13:55,554][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:13:56,062][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:13:56,569][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:13:57,074][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:13:57,582][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:13:58,091][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:13:58,600][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:13:59,108][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:13:59,617][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:14:00,125][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:14:00,633][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:14:01,142][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:14:01,651][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:14:02,161][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:14:02,670][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:14:03,181][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:14:03,692][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:14:04,201][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:14:04,711][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:14:05,222][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:14:05,732][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:14:06,242][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:14:06,751][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:14:07,262][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:14:07,771][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:14:08,281][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:14:08,792][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:14:09,301][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:14:09,810][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:14:10,319][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:14:10,828][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:14:11,336][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:14:11,844][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:14:12,353][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:14:12,861][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:14:13,369][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:14:13,876][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:14:14,386][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:14:14,896][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:14:15,405][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:14:15,917][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:14:16,428][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:14:16,938][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:14:17,448][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:14:17,959][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-26 01:14:18,613][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-26 01:14:19,358][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:14:19,360][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:14:19,362][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:14:20,252][__main__][INFO] - Iteration 444 took 1m 16s (9.73% Gen, 89.10% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 4m 16s. Estimated total time: 63h 43m 23s. Time estimates for 10 more iterations: 12m 44s, 100 more iterations: 2h 7m 26s, 500 more iterations: 10h 37m 13s. [2026-03-26 01:14:20,254][__main__][INFO] - Starting iteration 444. [2026-03-26 01:14:20,655][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:14:20,656][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:14:21,875][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:14:23,721][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:14:28,348][__main__][INFO] - Number of regex retries in iteration 444: 2 [2026-03-26 01:14:28,349][__main__][INFO] - agents played in iteration 444 are Bob, Alice [2026-03-26 01:14:29,540][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:14:30,168][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:14:30,634][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:14:31,147][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:14:31,657][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:14:32,165][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:14:32,675][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:14:33,184][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:14:33,694][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:14:34,203][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:14:34,712][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:14:35,221][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:14:35,731][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:14:36,241][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:14:36,750][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:14:37,261][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:14:37,771][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:14:38,281][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:14:38,790][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:14:39,299][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:14:39,809][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:14:40,318][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:14:40,827][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:14:41,338][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:14:41,847][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:14:42,356][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:14:42,868][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:14:43,379][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:14:43,890][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:14:44,399][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:14:44,910][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:14:45,421][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:14:45,930][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:14:46,441][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:14:46,949][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:14:47,457][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:14:47,965][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:14:48,475][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:14:48,983][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:14:49,491][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:14:49,998][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:14:50,506][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:14:51,016][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:14:51,526][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:14:52,037][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:14:52,548][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:14:53,058][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:14:53,569][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:14:54,079][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:14:54,588][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:14:55,097][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:14:55,607][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:14:56,116][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:14:56,626][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:14:57,136][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:14:57,646][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:14:58,155][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:14:58,664][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:14:59,175][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:14:59,685][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:15:00,193][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:15:00,702][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:15:01,214][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:15:01,724][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:15:02,235][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:15:02,746][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:15:03,255][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:15:03,764][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:15:04,274][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:15:04,784][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:15:05,292][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:15:05,801][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:15:06,310][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:15:06,821][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:15:07,330][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:15:07,840][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:15:08,350][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:15:08,859][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:15:09,370][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:15:09,878][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:15:10,386][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:15:10,897][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:15:11,406][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:15:11,916][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:15:12,426][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:15:12,936][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:15:13,446][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:15:13,955][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:15:14,466][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:15:14,977][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:15:15,488][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:15:15,999][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:15:16,508][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:15:17,020][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:15:17,532][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:15:18,042][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:15:18,555][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:15:19,066][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:15:19,576][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:15:20,084][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:15:20,593][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:15:21,102][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:15:21,611][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:15:22,120][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:15:22,630][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:15:23,140][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:15:23,650][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:15:24,160][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:15:24,672][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:15:25,183][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:15:25,694][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:15:26,205][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:15:26,716][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:15:27,226][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:15:27,738][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:15:28,249][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:15:28,759][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:15:29,269][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:15:29,779][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:15:30,288][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:15:30,798][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:15:31,307][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:15:31,816][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:15:32,327][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:15:32,839][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:15:33,347][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:15:33,858][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:15:34,368][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:15:34,879][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:15:35,389][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21712 tokens. [2026-03-26 01:15:36,048][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:05 [2026-03-26 01:15:36,799][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:15:36,801][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:15:36,803][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:15:37,523][__main__][INFO] - Iteration 445 took 1m 16s (10.01% Gen, 89.05% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 23m 1s. Estimated total time: 64h 3m 25s. Time estimates for 10 more iterations: 12m 48s, 100 more iterations: 2h 8m 6s, 500 more iterations: 10h 40m 34s. [2026-03-26 01:15:37,525][__main__][INFO] - Starting iteration 445. [2026-03-26 01:15:37,928][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:15:37,929][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:15:39,852][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:15:45,848][__main__][INFO] - Number of regex retries in iteration 445: 1 [2026-03-26 01:15:45,849][__main__][INFO] - agents played in iteration 445 are Bob, Alice [2026-03-26 01:15:46,829][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:15:47,471][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:15:47,938][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:15:48,454][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:15:48,966][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:15:49,476][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:15:49,985][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:15:50,496][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:15:51,006][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:15:51,517][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:15:52,025][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:15:52,534][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:15:53,042][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:15:53,550][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:15:54,058][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:15:54,566][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:15:55,074][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:15:55,582][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:15:56,093][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:15:56,603][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:15:57,113][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:15:57,623][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:15:58,134][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:15:58,645][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:15:59,155][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:15:59,665][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:16:00,175][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:16:00,683][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:16:01,193][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:16:01,700][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:16:02,208][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:16:02,717][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:16:03,226][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:16:03,736][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:16:04,246][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:16:04,756][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:16:05,265][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:16:05,775][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:16:06,287][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:16:06,798][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:16:07,308][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:16:07,818][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:16:08,325][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:16:08,836][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:16:09,345][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:16:09,853][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:16:10,362][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:16:10,871][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:16:11,379][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:16:11,889][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:16:12,398][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:16:12,908][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:16:13,418][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:16:13,927][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:16:14,437][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:16:14,946][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:16:15,456][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:16:15,965][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:16:16,477][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:16:16,986][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:16:17,496][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:16:18,006][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:16:18,515][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:16:19,024][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:16:19,535][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:16:20,046][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:16:20,558][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:16:21,067][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:16:21,578][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:16:22,088][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:16:22,600][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:16:23,110][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:16:23,622][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:16:24,133][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:16:24,642][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:16:25,151][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:16:25,659][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:16:26,167][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:16:26,677][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:16:27,185][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:16:27,692][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:16:28,200][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:16:28,709][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:16:29,218][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:16:29,726][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:16:30,235][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:16:30,745][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:16:31,255][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:16:31,764][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:16:32,273][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:16:32,782][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:16:33,290][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:16:33,797][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:16:34,306][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:16:34,815][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:16:35,323][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:16:35,832][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:16:36,342][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:16:36,853][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:16:37,362][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:16:37,872][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:16:38,382][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:16:38,890][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:16:39,399][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:16:39,910][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:16:40,419][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:16:40,927][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:16:41,437][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:16:41,946][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:16:42,454][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:16:42,963][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:16:43,474][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:16:43,983][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:16:44,491][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:16:45,000][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:16:45,510][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:16:46,019][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:16:46,528][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:16:47,037][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:16:47,546][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:16:48,056][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:16:48,566][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:16:49,076][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:16:49,585][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:16:50,094][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:16:50,603][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:16:51,114][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:16:51,624][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:16:52,134][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:16:52,644][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 01:16:53,312][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 01:16:54,062][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:16:54,064][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:16:54,065][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:16:54,784][__main__][INFO] - Iteration 446 took 1m 16s (10.30% Gen, 88.76% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 21m 9s. Estimated total time: 64h 2m 51s. Time estimates for 10 more iterations: 12m 48s, 100 more iterations: 2h 8m 5s, 500 more iterations: 10h 40m 28s. [2026-03-26 01:16:54,787][__main__][INFO] - Starting iteration 446. [2026-03-26 01:16:55,187][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:16:55,188][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:17:02,476][__main__][INFO] - Number of regex retries in iteration 446: 0 [2026-03-26 01:17:02,477][__main__][INFO] - agents played in iteration 446 are Bob, Alice [2026-03-26 01:17:03,432][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:17:04,065][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:17:04,529][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:17:05,043][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:17:05,552][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:17:06,061][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:17:06,570][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:17:07,078][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:17:07,587][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:17:08,096][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:17:08,605][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:17:09,114][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:17:09,623][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:17:10,133][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:17:10,641][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:17:11,151][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:17:11,658][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:17:12,167][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:17:12,676][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:17:13,185][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:17:13,694][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:17:14,203][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:17:14,713][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:17:15,223][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:17:15,733][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:17:16,243][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:17:16,752][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:17:17,261][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:17:17,769][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:17:18,277][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:17:18,785][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:17:19,293][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:17:19,801][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:17:20,309][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:17:20,821][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:17:21,333][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:17:21,843][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:17:22,354][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:17:22,865][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:17:23,376][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:17:23,886][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:17:24,397][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:17:24,906][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:17:25,415][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:17:25,924][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:17:26,433][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:17:26,942][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:17:27,452][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:17:27,961][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:17:28,469][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:17:28,979][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:17:29,489][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:17:29,998][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:17:30,506][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:17:31,017][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:17:31,525][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:17:32,035][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:17:32,545][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:17:33,055][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:17:33,564][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:17:34,072][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:17:34,581][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:17:35,090][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:17:35,599][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:17:36,107][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:17:36,617][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:17:37,127][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:17:37,637][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:17:38,146][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:17:38,656][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:17:39,165][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:17:39,673][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:17:40,181][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:17:40,690][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:17:41,198][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:17:41,706][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:17:42,215][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:17:42,724][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:17:43,232][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:17:43,742][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:17:44,251][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:17:44,759][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:17:45,267][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:17:45,777][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:17:46,286][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:17:46,796][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:17:47,304][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:17:47,814][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:17:48,323][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:17:48,832][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:17:49,340][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:17:49,848][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:17:50,356][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:17:50,863][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:17:51,372][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:17:51,880][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:17:52,387][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:17:52,894][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:17:53,404][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:17:53,915][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:17:54,426][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:17:54,937][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:17:55,448][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:17:55,958][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:17:56,468][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:17:56,979][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:17:57,487][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:17:57,997][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:17:58,505][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:17:59,014][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:17:59,523][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:18:00,031][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:18:00,540][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:18:01,049][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:18:01,558][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:18:02,066][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:18:02,574][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:18:03,084][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:18:03,592][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:18:04,100][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:18:04,608][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:18:05,117][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:18:05,625][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:18:06,136][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:18:06,645][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:18:07,155][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:18:07,663][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:18:08,172][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:18:08,682][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:18:09,190][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 01:18:09,851][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 01:18:10,591][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:18:10,593][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:18:10,595][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:18:11,316][__main__][INFO] - Iteration 447 took 1m 16s (9.57% Gen, 89.48% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 53h 43m 30s. Estimated total time: 63h 26m 28s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 52s, 500 more iterations: 10h 34m 24s. [2026-03-26 01:18:11,318][__main__][INFO] - Starting iteration 447. [2026-03-26 01:18:11,721][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:18:11,721][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:18:12,363][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:18:18,547][__main__][INFO] - Number of regex retries in iteration 447: 1 [2026-03-26 01:18:18,548][__main__][INFO] - agents played in iteration 447 are Bob, Alice [2026-03-26 01:18:19,501][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:18:20,135][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:18:20,600][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:18:21,116][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:18:21,625][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:18:22,137][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:18:22,646][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:18:23,156][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:18:23,667][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:18:24,176][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:18:24,685][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:18:25,194][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:18:25,703][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:18:26,212][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:18:26,722][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:18:27,230][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:18:27,740][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:18:28,248][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:18:28,760][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:18:29,270][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:18:29,778][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:18:30,287][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:18:30,796][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:18:31,303][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:18:31,813][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:18:32,323][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:18:32,834][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:18:33,344][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:18:33,853][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:18:34,363][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:18:34,873][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:18:35,383][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:18:35,892][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:18:36,401][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:18:36,911][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:18:37,421][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:18:37,932][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:18:38,442][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:18:38,951][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:18:39,461][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:18:39,971][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:18:40,481][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:18:40,990][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:18:41,500][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:18:42,009][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:18:42,518][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:18:43,027][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:18:43,537][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:18:44,047][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:18:44,558][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:18:45,068][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:18:45,577][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:18:46,086][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:18:46,597][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:18:47,106][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:18:47,615][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:18:48,125][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:18:48,635][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:18:49,146][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:18:49,656][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:18:50,165][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:18:50,675][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:18:51,183][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:18:51,694][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:18:52,204][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:18:52,716][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:18:53,226][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:18:53,736][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:18:54,246][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:18:54,756][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:18:55,266][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:18:55,777][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:18:56,287][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:18:56,798][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:18:57,307][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:18:57,816][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:18:58,326][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:18:58,836][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:18:59,345][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:18:59,855][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:19:00,364][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:19:00,872][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:19:01,382][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:19:01,891][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:19:02,401][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:19:02,910][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:19:03,420][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:19:03,929][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:19:04,439][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:19:04,950][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:19:05,460][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:19:05,968][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:19:06,478][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:19:06,987][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:19:07,496][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:19:08,004][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:19:08,515][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:19:09,025][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:19:09,534][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:19:10,043][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:19:10,553][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:19:11,064][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:19:11,573][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:19:12,083][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:19:12,592][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:19:13,101][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:19:13,609][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:19:14,118][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:19:14,628][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:19:15,138][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:19:15,647][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:19:16,156][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:19:16,666][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:19:17,176][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:19:17,684][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:19:18,194][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:19:18,703][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:19:19,213][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:19:19,722][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:19:20,232][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:19:20,741][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:19:21,253][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:19:21,765][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:19:22,274][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:19:22,784][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:19:23,294][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:19:23,804][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:19:24,316][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:19:24,827][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:19:25,337][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 01:19:26,006][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.65%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:05 [2026-03-26 01:19:26,756][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:19:26,758][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:19:26,760][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:19:27,416][__main__][INFO] - Iteration 448 took 1m 15s (9.02% Gen, 90.11% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 20m 34s. Estimated total time: 63h 4m 49s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 9s, 500 more iterations: 10h 30m 48s. [2026-03-26 01:19:27,418][__main__][INFO] - Starting iteration 448. [2026-03-26 01:19:27,818][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:19:27,819][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:19:28,434][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:19:29,772][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:19:35,392][__main__][INFO] - Number of regex retries in iteration 448: 2 [2026-03-26 01:19:35,393][__main__][INFO] - agents played in iteration 448 are Bob, Alice [2026-03-26 01:19:36,346][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:19:36,980][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:19:37,447][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:19:37,962][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:19:38,471][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:19:38,981][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:19:39,490][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:19:39,999][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:19:40,509][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:19:41,018][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:19:41,527][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:19:42,035][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:19:42,544][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:19:43,053][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:19:43,562][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:19:44,071][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:19:44,581][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:19:45,089][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:19:45,599][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:19:46,109][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:19:46,618][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:19:47,126][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:19:47,635][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:19:48,146][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:19:48,655][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:19:49,164][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:19:49,674][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:19:50,183][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:19:50,691][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:19:51,199][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:19:51,709][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:19:52,217][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:19:52,729][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:19:53,237][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:19:53,746][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:19:54,255][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:19:54,764][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:19:55,275][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:19:55,785][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:19:56,297][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:19:56,806][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:19:57,315][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:19:57,823][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:19:58,332][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:19:58,841][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:19:59,350][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:19:59,858][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:20:00,365][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:20:00,874][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:20:01,382][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:20:01,890][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:20:02,397][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:20:02,905][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:20:03,412][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:20:03,919][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:20:04,425][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:20:04,939][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:20:05,453][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:20:05,965][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:20:06,479][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:20:07,005][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:20:07,522][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:20:08,033][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:20:08,546][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:20:09,058][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:20:09,569][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:20:10,082][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:20:10,595][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:20:11,107][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:20:11,619][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:20:12,131][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:20:12,644][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:20:13,155][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:20:13,666][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:20:14,179][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:20:14,689][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:20:15,199][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:20:15,709][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:20:16,219][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:20:16,730][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:20:17,241][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:20:17,751][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:20:18,261][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:20:18,771][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:20:19,280][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:20:19,790][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:20:20,300][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:20:20,810][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:20:21,320][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:20:21,830][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:20:22,340][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:20:22,850][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:20:23,360][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:20:23,870][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:20:24,380][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:20:24,889][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:20:25,398][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:20:25,907][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:20:26,416][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:20:26,925][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:20:27,436][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:20:27,946][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:20:28,456][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:20:28,967][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:20:29,477][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:20:29,987][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:20:30,497][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:20:31,006][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:20:31,517][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:20:32,026][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:20:32,536][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:20:33,050][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:20:33,561][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:20:34,079][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:20:34,589][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:20:35,100][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:20:35,623][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:20:36,134][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:20:36,646][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:20:37,157][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:20:37,667][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:20:38,177][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:20:38,687][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:20:39,198][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:20:39,710][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:20:40,220][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:20:40,732][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:20:41,243][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:20:41,755][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:20:42,266][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21750 tokens. [2026-03-26 01:20:42,954][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:05 [2026-03-26 01:20:43,698][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:20:43,701][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:20:43,702][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:20:44,434][__main__][INFO] - Iteration 449 took 1m 16s (9.89% Gen, 89.16% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 5m 18s. Estimated total time: 63h 50m 49s. Time estimates for 10 more iterations: 12m 46s, 100 more iterations: 2h 7m 41s, 500 more iterations: 10h 38m 28s. [2026-03-26 01:20:44,436][__main__][INFO] - Starting iteration 449. [2026-03-26 01:20:44,838][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:20:44,838][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:20:52,163][__main__][INFO] - Number of regex retries in iteration 449: 0 [2026-03-26 01:20:52,164][__main__][INFO] - agents played in iteration 449 are Bob, Alice [2026-03-26 01:20:53,123][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:20:53,753][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:20:54,219][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:20:54,734][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:20:55,244][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:20:55,755][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:20:56,265][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:20:56,774][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:20:57,283][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:20:57,794][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:20:58,302][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:20:58,812][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:20:59,322][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:20:59,832][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:21:00,341][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:21:00,850][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:21:01,359][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:21:01,869][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:21:02,378][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:21:02,887][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:21:03,398][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:21:03,906][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:21:04,416][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:21:04,926][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:21:05,436][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:21:05,945][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:21:06,453][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:21:06,962][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:21:07,470][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:21:07,978][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:21:08,485][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:21:08,994][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:21:09,500][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:21:10,008][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:21:10,516][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:21:11,024][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:21:11,533][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:21:12,043][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:21:12,551][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:21:13,062][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:21:13,572][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:21:14,081][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:21:14,594][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:21:15,108][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:21:15,621][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:21:16,133][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:21:16,646][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:21:17,157][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:21:17,675][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:21:18,188][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:21:18,699][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:21:19,209][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:21:19,720][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:21:20,243][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:21:20,756][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:21:21,267][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:21:21,780][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:21:22,291][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:21:22,807][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:21:23,318][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:21:23,829][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:21:24,340][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:21:24,851][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:21:25,362][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:21:25,872][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:21:26,383][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:21:26,893][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:21:27,404][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:21:27,915][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:21:28,426][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:21:28,937][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:21:29,449][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:21:29,960][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:21:30,472][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:21:30,983][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:21:31,493][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:21:32,004][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:21:32,515][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:21:33,025][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:21:33,538][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:21:34,047][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:21:34,557][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:21:35,067][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:21:35,578][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:21:36,087][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:21:36,596][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:21:37,106][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:21:37,618][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:21:38,128][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:21:38,638][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:21:39,146][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:21:39,655][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:21:40,163][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:21:40,671][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:21:41,180][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:21:41,687][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:21:42,195][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:21:42,703][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:21:43,212][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:21:43,722][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:21:44,230][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:21:44,739][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:21:45,248][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:21:45,757][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:21:46,266][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:21:46,775][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:21:47,284][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:21:47,793][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:21:48,302][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:21:48,812][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:21:49,322][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:21:49,831][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:21:50,341][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:21:50,851][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:21:51,360][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:21:51,869][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:21:52,378][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:21:52,888][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:21:53,397][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:21:53,906][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:21:54,416][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:21:54,927][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:21:55,437][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:21:55,946][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:21:56,455][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:21:56,965][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:21:57,476][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:21:57,985][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:21:58,496][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:21:59,005][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-26 01:21:59,689][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:05 [2026-03-26 01:22:00,444][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:22:00,447][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:22:00,448][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:22:01,209][__main__][INFO] - Iteration 450 took 1m 16s (9.59% Gen, 89.41% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 53h 51m 47s. Estimated total time: 63h 38m 35s. Time estimates for 10 more iterations: 12m 43s, 100 more iterations: 2h 7m 17s, 500 more iterations: 10h 36m 25s. [2026-03-26 01:22:01,211][__main__][INFO] - Starting iteration 450. [2026-03-26 01:22:01,611][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 8 and human policies 1. [2026-03-26 01:22:01,612][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:22:02,841][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:22:06,915][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:22:08,725][__main__][INFO] - Number of regex retries in iteration 450: 2 [2026-03-26 01:22:08,726][__main__][INFO] - agents played in iteration 450 are Bob, Alice [2026-03-26 01:22:09,699][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:22:10,328][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:22:10,791][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:22:11,306][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:22:11,816][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:22:12,324][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:22:12,834][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:22:13,342][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:22:13,851][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:22:14,358][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:22:14,869][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:22:15,379][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:22:15,888][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:22:16,398][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:22:16,908][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:22:17,418][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:22:17,926][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:22:18,438][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:22:18,946][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:22:19,454][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:22:19,962][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:22:20,471][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:22:20,979][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:22:21,487][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:22:21,997][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:22:22,506][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:22:23,016][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:22:23,525][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:22:24,035][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:22:24,545][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:22:25,055][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:22:25,564][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:22:26,074][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:22:26,583][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:22:27,095][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:22:27,605][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:22:28,115][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:22:28,625][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:22:29,138][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:22:29,648][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:22:30,158][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:22:30,669][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:22:31,177][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:22:31,686][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:22:32,194][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:22:32,702][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:22:33,211][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:22:33,720][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:22:34,228][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:22:34,738][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:22:35,248][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:22:35,758][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:22:36,267][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:22:36,778][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:22:37,287][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:22:37,797][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:22:38,308][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:22:38,819][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:22:39,328][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:22:39,838][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:22:40,347][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:22:40,855][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:22:41,365][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:22:41,876][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:22:42,386][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:22:42,896][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:22:43,402][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:22:43,908][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:22:44,415][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:22:44,922][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:22:45,430][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:22:45,936][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:22:46,444][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:22:46,950][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:22:47,459][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:22:47,971][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:22:48,480][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:22:48,989][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:22:49,498][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:22:50,006][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:22:50,515][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:22:51,023][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:22:51,534][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:22:52,046][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:22:52,555][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:22:53,064][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:22:53,573][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:22:54,082][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:22:54,590][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:22:55,099][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:22:55,615][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:22:56,126][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:22:56,638][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:22:57,149][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:22:57,660][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:22:58,170][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:22:58,681][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:22:59,191][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:22:59,703][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:23:00,219][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:23:00,732][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:23:01,243][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:23:01,757][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:23:02,270][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:23:02,781][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:23:03,292][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:23:03,803][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:23:04,320][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:23:04,832][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:23:05,342][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:23:05,853][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:23:06,365][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:23:06,877][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:23:07,388][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:23:07,898][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:23:08,414][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:23:08,926][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:23:09,438][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:23:09,951][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:23:10,463][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:23:10,974][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:23:11,485][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:23:11,996][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:23:12,507][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:23:13,017][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:23:13,527][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:23:14,037][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:23:14,547][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:23:15,058][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:23:15,570][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 01:23:16,229][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 01:23:16,982][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:23:16,984][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:23:16,986][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:23:18,299][__main__][INFO] - Iteration 451 took 1m 16s (9.28% Gen, 89.01% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 6m 21s. Estimated total time: 63h 54m 26s. Time estimates for 10 more iterations: 12m 46s, 100 more iterations: 2h 7m 48s, 500 more iterations: 10h 39m 4s. [2026-03-26 01:23:18,301][__main__][INFO] - Starting iteration 451. [2026-03-26 01:23:18,704][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:23:18,705][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:23:25,448][__main__][INFO] - Number of regex retries in iteration 451: 0 [2026-03-26 01:23:25,449][__main__][INFO] - agents played in iteration 451 are Bob, Alice [2026-03-26 01:23:26,414][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:23:27,112][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:23:27,576][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:23:28,090][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:23:28,600][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:23:29,109][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:23:29,619][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:23:30,130][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:23:30,640][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:23:31,150][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:23:31,660][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:23:32,167][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:23:32,678][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:23:33,187][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:23:33,697][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:23:34,205][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:23:34,715][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:23:35,225][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:23:35,736][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:23:36,246][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:23:36,758][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:23:37,268][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:23:37,777][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:23:38,286][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:23:38,796][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:23:39,306][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:23:39,815][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:23:40,324][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:23:40,833][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:23:41,342][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:23:41,850][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:23:42,358][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:23:42,867][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:23:43,376][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:23:43,885][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:23:44,394][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:23:44,903][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:23:45,411][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:23:45,919][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:23:46,426][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:23:46,935][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:23:47,444][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:23:47,952][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:23:48,460][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:23:48,969][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:23:49,477][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:23:49,986][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:23:50,495][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:23:51,004][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:23:51,512][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:23:52,021][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:23:52,530][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:23:53,039][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:23:53,547][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:23:54,055][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:23:54,564][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:23:55,072][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:23:55,581][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:23:56,092][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:23:56,602][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:23:57,112][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:23:57,622][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:23:58,133][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:23:58,643][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:23:59,154][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:23:59,665][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:24:00,174][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:24:00,682][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:24:01,190][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:24:01,697][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:24:02,206][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:24:02,714][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:24:03,224][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:24:03,732][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:24:04,241][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:24:04,748][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:24:05,256][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:24:05,764][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:24:06,272][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:24:06,780][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:24:07,287][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:24:07,795][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:24:08,304][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:24:08,815][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:24:09,326][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:24:09,837][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:24:10,348][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:24:10,858][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:24:11,369][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:24:11,880][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:24:12,391][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:24:12,900][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:24:13,413][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:24:13,923][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:24:14,435][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:24:14,945][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:24:15,456][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:24:15,966][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:24:16,476][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:24:16,987][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:24:17,502][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:24:18,014][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:24:18,525][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:24:19,040][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:24:19,552][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:24:20,064][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:24:20,574][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:24:21,085][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:24:21,605][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:24:22,118][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:24:22,630][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:24:23,141][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:24:23,652][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:24:24,163][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:24:24,673][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:24:25,184][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:24:25,695][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:24:26,206][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:24:26,719][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:24:27,230][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:24:27,741][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:24:28,252][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:24:28,764][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:24:29,276][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:24:29,789][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:24:30,301][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:24:30,814][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:24:31,327][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:24:31,839][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:24:32,352][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21727 tokens. [2026-03-26 01:24:33,025][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.28%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:05 [2026-03-26 01:24:33,795][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:24:33,797][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:24:33,799][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:24:34,483][__main__][INFO] - Iteration 452 took 1m 15s (8.90% Gen, 90.20% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 19m 35s. Estimated total time: 63h 8m 56s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 17s, 500 more iterations: 10h 31m 29s. [2026-03-26 01:24:34,485][__main__][INFO] - Starting iteration 452. [2026-03-26 01:24:34,890][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:24:34,891][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:24:35,608][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:24:43,002][__main__][INFO] - Number of regex retries in iteration 452: 1 [2026-03-26 01:24:43,003][__main__][INFO] - agents played in iteration 452 are Bob, Alice [2026-03-26 01:24:43,957][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:24:44,594][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:24:45,093][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:24:45,606][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:24:46,115][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:24:46,625][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:24:47,133][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:24:47,643][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:24:48,151][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:24:48,662][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:24:49,169][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:24:49,680][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:24:50,189][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:24:50,698][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:24:51,206][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:24:51,714][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:24:52,223][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:24:52,731][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:24:53,243][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:24:53,752][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:24:54,261][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:24:54,771][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:24:55,281][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:24:55,791][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:24:56,301][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:24:56,811][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:24:57,320][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:24:57,830][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:24:58,339][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:24:58,847][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:24:59,358][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:24:59,868][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:25:00,376][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:25:00,885][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:25:01,394][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:25:01,902][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:25:02,411][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:25:02,919][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:25:03,427][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:25:03,935][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:25:04,444][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:25:04,954][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:25:05,461][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:25:05,968][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:25:06,473][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:25:06,981][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:25:07,487][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:25:07,994][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:25:08,501][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:25:09,008][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:25:09,517][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:25:10,027][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:25:10,537][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:25:11,046][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:25:11,555][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:25:12,065][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:25:12,573][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:25:13,081][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:25:13,590][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:25:14,097][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:25:14,604][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:25:15,113][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:25:15,621][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:25:16,129][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:25:16,637][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:25:17,146][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:25:17,655][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:25:18,163][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:25:18,672][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:25:19,180][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:25:19,688][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:25:20,196][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:25:20,705][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:25:21,214][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:25:21,723][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:25:22,229][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:25:22,738][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:25:23,246][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:25:23,754][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:25:24,262][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:25:24,771][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:25:25,280][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:25:25,788][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:25:26,298][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:25:26,806][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:25:27,316][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:25:27,824][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:25:28,336][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:25:28,845][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:25:29,355][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:25:29,865][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:25:30,375][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:25:30,883][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:25:31,391][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:25:31,900][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:25:32,409][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:25:32,918][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:25:33,428][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:25:33,937][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:25:34,447][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:25:34,954][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:25:35,463][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:25:35,970][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:25:36,478][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:25:36,986][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:25:37,495][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:25:38,002][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:25:38,509][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:25:39,015][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:25:39,521][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:25:40,032][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:25:40,540][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:25:41,049][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:25:41,557][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:25:42,069][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:25:42,578][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:25:43,088][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:25:43,599][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:25:44,114][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:25:44,626][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:25:45,138][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:25:45,649][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:25:46,159][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:25:46,668][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:25:47,177][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:25:47,688][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:25:48,201][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:25:48,713][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:25:49,222][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:25:49,732][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 01:25:50,411][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.16%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.23%, ΔTime: 00:01:05 [2026-03-26 01:25:51,162][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:25:51,164][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:25:51,166][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:25:51,848][__main__][INFO] - Iteration 453 took 1m 16s (10.54% Gen, 88.57% Train). Generation: 8s, Training: 1m 8s. Estimated remaining time: 54h 17m 19s. Estimated total time: 64h 7m 57s. Time estimates for 10 more iterations: 12m 49s, 100 more iterations: 2h 8m 15s, 500 more iterations: 10h 41m 19s. [2026-03-26 01:25:51,851][__main__][INFO] - Starting iteration 453. [2026-03-26 01:25:52,253][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:25:52,254][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:25:59,815][__main__][INFO] - Number of regex retries in iteration 453: 0 [2026-03-26 01:25:59,816][__main__][INFO] - agents played in iteration 453 are Bob, Alice [2026-03-26 01:26:00,783][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:26:01,409][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:26:01,876][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:26:02,388][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:26:02,896][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:26:03,405][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:26:03,914][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:26:04,422][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:26:04,930][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:26:05,439][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:26:05,951][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:26:06,461][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:26:06,972][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:26:07,481][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:26:07,991][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:26:08,501][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:26:09,010][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:26:09,520][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:26:10,031][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:26:10,541][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:26:11,051][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:26:11,561][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:26:12,071][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:26:12,581][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:26:13,090][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:26:13,600][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:26:14,128][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:26:14,644][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:26:15,154][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:26:15,665][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:26:16,175][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:26:16,685][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:26:17,197][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:26:17,709][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:26:18,220][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:26:18,729][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:26:19,239][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:26:19,752][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:26:20,262][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:26:20,771][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:26:21,280][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:26:21,789][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:26:22,299][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:26:22,807][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:26:23,316][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:26:23,825][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:26:24,337][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:26:24,847][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:26:25,356][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:26:25,866][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:26:26,375][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:26:26,884][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:26:27,393][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:26:27,903][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:26:28,412][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:26:28,921][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:26:29,430][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:26:29,941][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:26:30,451][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:26:30,958][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:26:31,466][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:26:31,975][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:26:32,483][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:26:32,992][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:26:33,500][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:26:34,008][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:26:34,516][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:26:35,024][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:26:35,533][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:26:36,043][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:26:36,551][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:26:37,059][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:26:37,568][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:26:38,077][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:26:38,587][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:26:39,097][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:26:39,606][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:26:40,115][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:26:40,624][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:26:41,136][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:26:41,646][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:26:42,155][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:26:42,665][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:26:43,175][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:26:43,685][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:26:44,194][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:26:44,703][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:26:45,214][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:26:45,725][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:26:46,235][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:26:46,746][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:26:47,256][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:26:47,766][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:26:48,277][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:26:48,787][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:26:49,297][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:26:49,806][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:26:50,319][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:26:50,830][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:26:51,341][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:26:51,852][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:26:52,363][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:26:52,874][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:26:53,385][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:26:53,896][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:26:54,413][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:26:54,925][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:26:55,436][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:26:55,947][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:26:56,457][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:26:56,967][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:26:57,478][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:26:57,987][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:26:58,504][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:26:59,016][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:26:59,527][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:27:00,040][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:27:00,552][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:27:01,063][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:27:01,573][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:27:02,084][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:27:02,610][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:27:03,121][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:27:03,632][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:27:04,142][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:27:04,654][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:27:05,165][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:27:05,675][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:27:06,185][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:27:06,698][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 01:27:07,368][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:05 [2026-03-26 01:27:08,114][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:27:08,116][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:27:08,118][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:27:08,898][__main__][INFO] - Iteration 454 took 1m 16s (9.87% Gen, 89.11% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 54h 0m 19s. Estimated total time: 63h 52m 15s. Time estimates for 10 more iterations: 12m 46s, 100 more iterations: 2h 7m 44s, 500 more iterations: 10h 38m 42s. [2026-03-26 01:27:08,900][__main__][INFO] - Starting iteration 454. [2026-03-26 01:27:09,299][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:27:09,299][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:27:12,956][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:27:16,692][__main__][INFO] - Number of regex retries in iteration 454: 1 [2026-03-26 01:27:16,693][__main__][INFO] - agents played in iteration 454 are Bob, Alice [2026-03-26 01:27:17,656][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:27:18,272][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:27:18,736][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:27:19,249][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:27:19,757][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:27:20,266][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:27:20,775][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:27:21,282][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:27:21,789][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:27:22,297][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:27:22,808][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:27:23,318][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:27:23,826][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:27:24,335][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:27:24,844][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:27:25,353][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:27:25,861][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:27:26,370][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:27:26,880][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:27:27,388][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:27:27,898][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:27:28,408][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:27:28,917][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:27:29,426][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:27:29,935][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:27:30,444][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:27:30,951][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:27:31,458][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:27:31,966][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:27:32,474][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:27:32,981][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:27:33,488][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:27:33,996][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:27:34,504][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:27:35,012][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:27:35,520][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:27:36,026][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:27:36,535][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:27:37,045][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:27:37,553][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:27:38,061][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:27:38,569][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:27:39,096][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:27:39,609][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:27:40,117][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:27:40,624][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:27:41,135][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:27:41,644][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:27:42,153][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:27:42,662][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:27:43,170][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:27:43,678][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:27:44,186][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:27:44,695][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:27:45,204][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:27:45,711][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:27:46,220][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:27:46,729][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:27:47,237][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:27:47,744][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:27:48,252][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:27:48,759][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:27:49,267][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:27:49,774][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:27:50,281][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:27:50,788][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:27:51,296][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:27:51,805][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:27:52,312][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:27:52,821][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:27:53,329][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:27:53,838][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:27:54,345][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:27:54,853][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:27:55,363][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:27:55,872][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:27:56,380][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:27:56,889][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:27:57,397][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:27:57,905][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:27:58,416][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:27:58,925][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:27:59,435][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:27:59,943][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:28:00,452][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:28:00,962][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:28:01,470][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:28:01,979][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:28:02,487][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:28:02,996][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:28:03,504][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:28:04,014][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:28:04,523][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:28:05,031][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:28:05,540][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:28:06,049][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:28:06,558][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:28:07,066][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:28:07,573][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:28:08,081][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:28:08,589][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:28:09,098][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:28:09,605][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:28:10,114][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:28:10,622][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:28:11,129][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:28:11,639][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:28:12,147][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:28:12,657][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:28:13,166][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:28:13,676][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:28:14,186][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:28:14,695][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:28:15,203][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:28:15,711][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:28:16,219][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:28:16,728][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:28:17,237][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:28:17,747][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:28:18,256][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:28:18,766][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:28:19,275][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:28:19,783][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:28:20,290][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:28:20,804][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:28:21,315][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:28:21,824][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:28:22,334][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:28:22,843][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:28:23,351][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 01:28:24,009][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-26 01:28:24,762][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:28:24,765][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:28:24,766][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:28:25,429][__main__][INFO] - Iteration 455 took 1m 16s (9.71% Gen, 89.42% Train). Generation: 7s, Training: 1m 8s. Estimated remaining time: 53h 33m 22s. Estimated total time: 63h 26m 34s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 53s, 500 more iterations: 10h 34m 25s. [2026-03-26 01:28:25,432][__main__][INFO] - Starting iteration 455. [2026-03-26 01:28:25,832][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:28:25,833][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:28:32,565][__main__][INFO] - Number of regex retries in iteration 455: 0 [2026-03-26 01:28:32,567][__main__][INFO] - agents played in iteration 455 are Bob, Alice [2026-03-26 01:28:33,816][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:28:34,444][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:28:34,910][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:28:35,424][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:28:35,938][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:28:36,448][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:28:36,957][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:28:37,467][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:28:37,977][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:28:38,488][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:28:39,000][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:28:39,511][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:28:40,021][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:28:40,530][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:28:41,040][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:28:41,550][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:28:42,060][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:28:42,570][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:28:43,080][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:28:43,590][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:28:44,100][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:28:44,609][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:28:45,118][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:28:45,628][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:28:46,139][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:28:46,649][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:28:47,159][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:28:47,668][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:28:48,178][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:28:48,688][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:28:49,196][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:28:49,705][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:28:50,217][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:28:50,728][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:28:51,239][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:28:51,749][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:28:52,259][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:28:52,770][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:28:53,279][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:28:53,790][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:28:54,300][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:28:54,810][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:28:55,319][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:28:55,828][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:28:56,337][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:28:56,847][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:28:57,357][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:28:57,868][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:28:58,377][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:28:58,887][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:28:59,396][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:28:59,906][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:29:00,414][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:29:00,923][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:29:01,434][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:29:01,944][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:29:02,453][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:29:02,962][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:29:03,471][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:29:03,980][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:29:04,488][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:29:04,997][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:29:05,505][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:29:06,014][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:29:06,523][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:29:07,032][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:29:07,541][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:29:08,050][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:29:08,560][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:29:09,070][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:29:09,579][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:29:10,088][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:29:10,597][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:29:11,106][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:29:11,617][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:29:12,127][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:29:12,636][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:29:13,146][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:29:13,656][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:29:14,165][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:29:14,675][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:29:15,184][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:29:15,694][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:29:16,204][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:29:16,713][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:29:17,223][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:29:17,733][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:29:18,246][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:29:18,757][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:29:19,268][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:29:19,778][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:29:20,290][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:29:20,799][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:29:21,308][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:29:21,817][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:29:22,333][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:29:22,844][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:29:23,355][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:29:23,868][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:29:24,380][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:29:24,892][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:29:25,403][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:29:25,917][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:29:26,435][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:29:26,948][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:29:27,461][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:29:27,973][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:29:28,484][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:29:28,997][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:29:29,510][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:29:30,024][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:29:30,537][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:29:31,049][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:29:31,560][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:29:32,071][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:29:32,583][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:29:33,093][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:29:33,603][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:29:34,116][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:29:34,627][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:29:35,139][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:29:35,650][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:29:36,161][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:29:36,672][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:29:37,183][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:29:37,693][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:29:38,203][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:29:38,715][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:29:39,225][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:29:39,736][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21746 tokens. [2026-03-26 01:29:40,394][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:05 [2026-03-26 01:29:41,145][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:29:41,147][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:29:41,149][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:29:41,864][__main__][INFO] - Iteration 456 took 1m 16s (8.86% Gen, 90.20% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 27m 9s. Estimated total time: 63h 21m 37s. Time estimates for 10 more iterations: 12m 40s, 100 more iterations: 2h 6m 43s, 500 more iterations: 10h 33m 36s. [2026-03-26 01:29:41,866][__main__][INFO] - Starting iteration 456. [2026-03-26 01:29:42,268][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:29:42,269][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:29:44,017][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:29:49,215][__main__][INFO] - Number of regex retries in iteration 456: 1 [2026-03-26 01:29:49,216][__main__][INFO] - agents played in iteration 456 are Bob, Alice [2026-03-26 01:29:50,165][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:29:51,075][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:29:51,539][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:29:52,053][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:29:52,561][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:29:53,069][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:29:53,577][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:29:54,084][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:29:54,591][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:29:55,099][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:29:55,609][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:29:56,116][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:29:56,624][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:29:57,133][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:29:57,641][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:29:58,149][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:29:58,658][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:29:59,166][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:29:59,675][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:30:00,183][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:30:00,691][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:30:01,200][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:30:01,708][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:30:02,217][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:30:02,724][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:30:03,234][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:30:03,744][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:30:04,254][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:30:04,763][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:30:05,272][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:30:05,780][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:30:06,288][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:30:06,799][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:30:07,308][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:30:07,815][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:30:08,322][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:30:08,829][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:30:09,336][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:30:09,844][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:30:10,351][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:30:10,858][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:30:11,366][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:30:11,874][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:30:12,383][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:30:12,891][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:30:13,399][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:30:13,907][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:30:14,416][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:30:14,924][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:30:15,434][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:30:15,943][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:30:16,450][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:30:16,957][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:30:17,465][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:30:17,973][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:30:18,481][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:30:18,989][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:30:19,497][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:30:20,005][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:30:20,516][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:30:21,025][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:30:21,533][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:30:22,042][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:30:22,550][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:30:23,059][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:30:23,567][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:30:24,075][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:30:24,582][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:30:25,090][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:30:25,598][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:30:26,105][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:30:26,612][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:30:27,119][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:30:27,626][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:30:28,135][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:30:28,643][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:30:29,151][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:30:29,659][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:30:30,167][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:30:30,676][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:30:31,183][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:30:31,692][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:30:32,199][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:30:32,706][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:30:33,212][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:30:33,722][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:30:34,229][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:30:34,738][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:30:35,245][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:30:35,754][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:30:36,265][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:30:36,776][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:30:37,287][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:30:37,797][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:30:38,306][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:30:38,817][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:30:39,326][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:30:39,837][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:30:40,352][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:30:40,861][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:30:41,370][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:30:41,879][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:30:42,389][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:30:42,898][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:30:43,407][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:30:43,918][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:30:44,429][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:30:44,940][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:30:45,450][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:30:45,961][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:30:46,470][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:30:46,981][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:30:47,491][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:30:48,001][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:30:48,521][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:30:49,031][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:30:49,542][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:30:50,052][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:30:50,562][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:30:51,072][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:30:51,581][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:30:52,091][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:30:52,601][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:30:53,111][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:30:53,620][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:30:54,130][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:30:54,640][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:30:55,149][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:30:55,659][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:30:56,169][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 01:30:56,834][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.26%, ΔTime: 00:01:05 [2026-03-26 01:30:57,575][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:30:57,578][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:30:57,579][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:30:58,424][__main__][INFO] - Iteration 457 took 1m 16s (9.12% Gen, 89.77% Train). Generation: 6s, Training: 1m 8s. Estimated remaining time: 53h 32m 5s. Estimated total time: 63h 27m 50s. Time estimates for 10 more iterations: 12m 41s, 100 more iterations: 2h 6m 55s, 500 more iterations: 10h 34m 38s. [2026-03-26 01:30:58,426][__main__][INFO] - Starting iteration 457. [2026-03-26 01:30:58,828][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:30:58,829][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:31:06,054][__main__][INFO] - Number of regex retries in iteration 457: 0 [2026-03-26 01:31:06,055][__main__][INFO] - agents played in iteration 457 are Bob, Alice [2026-03-26 01:31:07,010][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:31:07,637][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:31:08,102][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:31:08,617][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:31:09,127][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:31:09,639][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:31:10,148][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:31:10,658][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:31:11,167][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:31:11,675][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:31:12,183][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:31:12,692][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:31:13,201][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:31:13,709][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:31:14,217][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:31:14,725][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:31:15,233][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:31:15,742][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:31:16,249][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:31:16,757][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:31:17,265][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:31:17,773][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:31:18,281][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:31:18,789][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:31:19,297][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:31:19,804][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:31:20,314][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:31:20,822][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:31:21,330][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:31:21,839][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:31:22,347][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:31:22,855][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:31:23,364][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:31:23,873][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:31:24,383][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:31:24,892][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:31:25,400][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:31:25,907][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:31:26,415][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:31:26,924][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:31:27,433][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:31:27,942][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:31:28,453][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:31:28,963][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:31:29,473][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:31:29,982][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:31:30,492][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:31:31,000][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:31:31,509][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:31:32,018][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:31:32,527][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:31:33,038][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:31:33,548][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:31:34,057][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:31:34,565][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:31:35,075][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:31:35,584][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:31:36,094][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:31:36,601][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:31:37,108][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:31:37,615][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:31:38,123][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:31:38,632][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:31:39,139][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:31:39,647][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:31:40,155][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:31:40,663][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:31:41,169][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:31:41,674][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:31:42,179][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:31:42,682][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:31:43,184][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:31:43,687][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:31:44,190][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:31:44,695][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:31:45,200][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:31:45,704][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:31:46,210][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:31:46,715][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:31:47,220][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:31:47,724][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:31:48,230][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:31:48,735][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:31:49,240][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:31:49,745][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:31:50,250][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:31:50,754][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:31:51,259][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:31:51,763][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:31:52,272][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:31:52,778][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:31:53,283][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:31:53,788][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:31:54,293][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:31:54,799][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:31:55,303][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:31:55,807][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:31:56,312][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:31:56,823][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:31:57,329][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:31:57,836][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:31:58,343][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:31:58,849][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:31:59,355][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:31:59,862][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:32:00,368][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:32:00,883][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:32:01,390][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:32:01,898][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:32:02,406][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:32:02,913][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:32:03,421][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:32:03,928][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:32:04,437][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:32:04,944][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:32:05,460][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:32:05,968][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:32:06,477][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:32:06,985][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:32:07,495][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:32:08,002][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:32:08,509][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:32:09,017][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:32:09,522][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:32:10,027][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:32:10,532][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:32:11,038][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:32:11,545][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:32:12,051][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:32:12,555][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-26 01:32:13,193][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-26 01:32:13,954][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:32:13,957][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:32:13,958][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:32:14,845][__main__][INFO] - Iteration 458 took 1m 16s (9.51% Gen, 89.33% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 53h 23m 52s. Estimated total time: 63h 20m 53s. Time estimates for 10 more iterations: 12m 40s, 100 more iterations: 2h 6m 41s, 500 more iterations: 10h 33m 28s. [2026-03-26 01:32:14,847][__main__][INFO] - Starting iteration 458. [2026-03-26 01:32:15,246][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:32:15,247][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:32:22,441][__main__][INFO] - Number of regex retries in iteration 458: 0 [2026-03-26 01:32:22,442][__main__][INFO] - agents played in iteration 458 are Bob, Alice [2026-03-26 01:32:23,349][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:32:23,931][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:32:24,389][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:32:24,899][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:32:25,403][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:32:25,907][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:32:26,413][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:32:26,917][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:32:27,422][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:32:27,926][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:32:28,434][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:32:28,941][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:32:29,447][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:32:29,953][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:32:30,461][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:32:30,967][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:32:31,474][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:32:31,979][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:32:32,485][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:32:32,988][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:32:33,493][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:32:33,997][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:32:34,502][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:32:35,006][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:32:35,511][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:32:36,017][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:32:36,523][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:32:37,031][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:32:37,537][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:32:38,042][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:32:38,548][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:32:39,054][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:32:39,560][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:32:40,065][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:32:40,569][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:32:41,070][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:32:41,577][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:32:42,082][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:32:42,590][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:32:43,095][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:32:43,598][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:32:44,105][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:32:44,608][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:32:45,113][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:32:45,617][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:32:46,121][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:32:46,625][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:32:47,127][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:32:47,633][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:32:48,137][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:32:48,642][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:32:49,145][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:32:49,649][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:32:50,153][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:32:50,658][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:32:51,163][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:32:51,666][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:32:52,170][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:32:52,676][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:32:53,180][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:32:53,684][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:32:54,188][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:32:54,692][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:32:55,196][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:32:55,702][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:32:56,205][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:32:56,709][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:32:57,213][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:32:57,718][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:32:58,222][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:32:58,727][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:32:59,230][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:32:59,741][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:33:00,246][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:33:00,755][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:33:01,262][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:33:01,769][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:33:02,275][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:33:02,783][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:33:03,291][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:33:03,797][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:33:04,300][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:33:04,803][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:33:05,305][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:33:05,806][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:33:06,308][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:33:06,810][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:33:07,312][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:33:07,823][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:33:08,328][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:33:08,832][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:33:09,337][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:33:09,841][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:33:10,345][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:33:10,849][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:33:11,354][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:33:11,872][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:33:12,376][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:33:12,879][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:33:13,382][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:33:13,886][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:33:14,390][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:33:14,893][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:33:15,396][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:33:15,899][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:33:16,401][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:33:16,902][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:33:17,403][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:33:17,904][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:33:18,405][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:33:18,907][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:33:19,408][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:33:19,908][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:33:20,412][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:33:20,914][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:33:21,415][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:33:21,916][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:33:22,418][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:33:22,919][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:33:23,420][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:33:23,921][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:33:24,423][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:33:24,923][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:33:25,424][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:33:25,924][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:33:26,424][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:33:26,926][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:33:27,427][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:33:27,928][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:33:28,428][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21727 tokens. [2026-03-26 01:33:29,039][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:05 [2026-03-26 01:33:29,836][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:33:29,838][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:33:29,840][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:33:30,493][__main__][INFO] - Iteration 459 took 1m 15s (9.56% Gen, 89.57% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 44m 5s. Estimated total time: 62h 42m 22s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 24s, 500 more iterations: 10h 27m 3s. [2026-03-26 01:33:30,495][__main__][INFO] - Starting iteration 459. [2026-03-26 01:33:30,893][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:33:30,894][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:33:37,773][__main__][INFO] - Number of regex retries in iteration 459: 0 [2026-03-26 01:33:37,774][__main__][INFO] - agents played in iteration 459 are Bob, Alice [2026-03-26 01:33:38,681][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:33:39,255][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:33:39,713][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:33:40,219][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:33:40,722][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:33:41,226][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:33:41,728][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:33:42,229][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:33:42,733][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:33:43,234][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:33:43,735][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:33:44,237][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:33:44,738][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:33:45,239][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:33:45,740][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:33:46,242][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:33:46,743][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:33:47,246][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:33:47,747][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:33:48,247][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:33:48,747][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:33:49,248][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:33:49,749][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:33:50,250][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:33:50,751][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:33:51,252][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:33:51,753][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:33:52,253][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:33:52,754][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:33:53,255][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:33:53,755][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:33:54,257][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:33:54,758][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:33:55,258][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:33:55,760][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:33:56,260][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:33:56,761][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:33:57,263][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:33:57,765][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:33:58,265][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:33:58,766][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:33:59,267][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:33:59,769][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:34:00,270][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:34:00,771][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:34:01,273][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:34:01,774][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:34:02,275][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:34:02,777][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:34:03,278][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:34:03,781][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:34:04,283][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:34:04,784][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:34:05,286][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:34:05,788][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:34:06,289][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:34:06,791][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:34:07,295][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:34:07,801][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:34:08,305][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:34:08,808][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:34:09,311][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:34:09,814][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:34:10,317][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:34:10,820][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:34:11,325][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:34:11,827][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:34:12,329][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:34:12,830][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:34:13,332][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:34:13,833][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:34:14,335][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:34:14,836][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:34:15,337][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:34:15,839][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:34:16,340][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:34:16,841][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:34:17,343][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:34:17,844][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:34:18,348][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:34:18,850][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:34:19,354][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:34:19,856][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:34:20,356][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:34:20,857][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:34:21,359][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:34:21,860][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:34:22,365][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:34:22,866][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:34:23,368][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:34:23,871][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:34:24,373][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:34:24,876][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:34:25,378][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:34:25,881][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:34:26,390][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:34:26,893][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:34:27,396][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:34:27,899][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:34:28,402][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:34:28,904][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:34:29,406][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:34:29,908][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:34:30,424][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:34:30,927][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:34:31,430][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:34:31,934][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:34:32,437][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:34:32,941][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:34:33,445][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:34:33,948][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:34:34,451][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:34:34,955][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:34:35,458][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:34:35,961][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:34:36,464][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:34:36,968][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:34:37,470][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:34:37,975][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:34:38,478][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:34:38,981][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:34:39,483][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:34:39,985][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:34:40,488][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:34:40,993][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:34:41,498][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:34:42,001][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:34:42,503][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:34:43,005][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:34:43,507][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 01:34:44,124][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.66%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 01:34:44,864][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:34:44,866][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:34:44,868][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:34:45,639][__main__][INFO] - Iteration 460 took 1m 14s (9.20% Gen, 89.76% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 52h 17m 46s. Estimated total time: 62h 17m 19s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 34s, 500 more iterations: 10h 22m 53s. [2026-03-26 01:34:45,641][__main__][INFO] - Starting iteration 460. [2026-03-26 01:34:46,041][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:34:46,042][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:34:52,224][mllm.models.large_language_model_local][WARNING] - Response Given the values, it's in your best interest to negotiate a fair split since both you and Bob value hats and books highly. A balanced approach might be to split the items evenly. Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:34:53,411][__main__][INFO] - Number of regex retries in iteration 460: 1 [2026-03-26 01:34:53,412][__main__][INFO] - agents played in iteration 460 are Bob, Alice [2026-03-26 01:34:54,317][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:34:54,893][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:34:55,349][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:34:55,855][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:34:56,355][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:34:56,858][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:34:57,358][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:34:57,859][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:34:58,359][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:34:58,860][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:34:59,363][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:34:59,864][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:35:00,366][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:35:00,867][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:35:01,370][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:35:01,871][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:35:02,372][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:35:02,873][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:35:03,375][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:35:03,876][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:35:04,377][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:35:04,878][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:35:05,380][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:35:05,882][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:35:06,382][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:35:06,883][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:35:07,388][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:35:07,892][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:35:08,395][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:35:08,896][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:35:09,398][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:35:09,900][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:35:10,402][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:35:10,904][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:35:11,432][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:35:11,937][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:35:12,441][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:35:12,944][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:35:13,447][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:35:13,950][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:35:14,454][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:35:14,958][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:35:15,459][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:35:15,959][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:35:16,461][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:35:16,962][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:35:17,462][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:35:17,964][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:35:18,464][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:35:18,964][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:35:19,465][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:35:19,966][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:35:20,467][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:35:20,968][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:35:21,469][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:35:21,969][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:35:22,470][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:35:22,970][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:35:23,472][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:35:23,973][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:35:24,475][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:35:24,975][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:35:25,476][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:35:25,977][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:35:26,478][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:35:26,979][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:35:27,481][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:35:27,981][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:35:28,482][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:35:28,982][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:35:29,482][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:35:29,983][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:35:30,483][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:35:30,983][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:35:31,484][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:35:31,985][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:35:32,486][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:35:32,992][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:35:33,494][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:35:33,996][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:35:34,499][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:35:35,001][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:35:35,502][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:35:36,003][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:35:36,506][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:35:37,011][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:35:37,516][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:35:38,019][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:35:38,522][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:35:39,023][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:35:39,527][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:35:40,029][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:35:40,532][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:35:41,035][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:35:41,544][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:35:42,049][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:35:42,553][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:35:43,057][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:35:43,563][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:35:44,069][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:35:44,575][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:35:45,080][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:35:45,596][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:35:46,102][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:35:46,608][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:35:47,116][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:35:47,619][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:35:48,121][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:35:48,624][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:35:49,126][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:35:49,633][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:35:50,135][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:35:50,638][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:35:51,140][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:35:51,642][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:35:52,145][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:35:52,648][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:35:53,149][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:35:53,653][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:35:54,156][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:35:54,659][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:35:55,161][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:35:55,663][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:35:56,164][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:35:56,665][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:35:57,167][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:35:57,668][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:35:58,169][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:35:58,670][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:35:59,172][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21718 tokens. [2026-03-26 01:35:59,782][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:04 [2026-03-26 01:36:00,575][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:36:00,578][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:36:00,579][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:36:01,238][__main__][INFO] - Iteration 461 took 1m 15s (9.80% Gen, 89.32% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 39m 5s. Estimated total time: 62h 39m 53s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 19s, 500 more iterations: 10h 26m 38s. [2026-03-26 01:36:01,240][__main__][INFO] - Starting iteration 461. [2026-03-26 01:36:01,638][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:36:01,639][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:36:08,815][__main__][INFO] - Number of regex retries in iteration 461: 0 [2026-03-26 01:36:08,816][__main__][INFO] - agents played in iteration 461 are Bob, Alice [2026-03-26 01:36:09,728][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:36:10,303][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:36:10,760][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:36:11,267][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:36:11,769][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:36:12,271][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:36:12,773][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:36:13,274][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:36:13,775][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:36:14,277][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:36:14,778][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:36:15,280][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:36:15,782][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:36:16,283][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:36:16,784][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:36:17,284][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:36:17,785][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:36:18,287][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:36:18,788][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:36:19,290][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:36:19,791][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:36:20,291][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:36:20,792][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:36:21,294][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:36:21,795][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:36:22,296][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:36:22,799][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:36:23,301][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:36:23,802][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:36:24,304][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:36:24,806][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:36:25,308][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:36:25,811][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:36:26,314][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:36:26,816][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:36:27,318][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:36:27,821][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:36:28,324][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:36:28,825][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:36:29,327][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:36:29,828][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:36:30,330][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:36:30,833][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:36:31,334][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:36:31,836][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:36:32,338][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:36:32,839][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:36:33,341][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:36:33,843][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:36:34,344][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:36:34,845][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:36:35,344][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:36:35,845][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:36:36,346][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:36:36,846][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:36:37,347][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:36:37,847][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:36:38,348][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:36:38,849][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:36:39,352][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:36:39,854][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:36:40,356][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:36:40,858][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:36:41,362][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:36:41,864][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:36:42,365][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:36:42,867][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:36:43,369][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:36:43,870][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:36:44,372][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:36:44,872][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:36:45,374][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:36:45,875][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:36:46,377][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:36:46,878][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:36:47,379][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:36:47,880][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:36:48,381][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:36:48,882][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:36:49,383][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:36:49,884][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:36:50,385][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:36:50,887][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:36:51,388][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:36:51,890][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:36:52,391][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:36:52,892][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:36:53,394][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:36:53,897][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:36:54,399][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:36:54,902][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:36:55,403][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:36:55,905][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:36:56,406][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:36:56,908][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:36:57,412][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:36:57,914][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:36:58,416][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:36:58,918][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:36:59,419][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:36:59,921][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:37:00,422][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:37:00,924][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:37:01,426][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:37:01,927][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:37:02,429][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:37:02,929][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:37:03,433][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:37:03,935][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:37:04,437][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:37:04,938][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:37:05,439][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:37:05,940][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:37:06,442][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:37:06,946][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:37:07,450][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:37:07,952][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:37:08,455][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:37:08,956][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:37:09,459][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:37:09,962][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:37:10,464][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:37:10,965][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:37:11,469][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:37:11,972][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:37:12,473][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:37:12,975][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:37:13,476][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:37:13,977][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:37:14,479][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21750 tokens. [2026-03-26 01:37:15,083][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.23%, ΔTime: 00:01:04 [2026-03-26 01:37:15,818][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:37:15,821][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:37:15,822][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:37:16,546][__main__][INFO] - Iteration 462 took 1m 14s (9.58% Gen, 89.45% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 23m 22s. Estimated total time: 62h 25m 25s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 50s, 500 more iterations: 10h 24m 14s. [2026-03-26 01:37:16,548][__main__][INFO] - Starting iteration 462. [2026-03-26 01:37:16,947][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:37:16,948][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:37:17,537][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:37:21,514][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:37:23,769][__main__][INFO] - Number of regex retries in iteration 462: 2 [2026-03-26 01:37:23,770][__main__][INFO] - agents played in iteration 462 are Bob, Alice [2026-03-26 01:37:24,680][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:37:25,264][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:37:25,724][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:37:26,232][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:37:26,735][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:37:27,239][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:37:27,742][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:37:28,245][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:37:28,748][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:37:29,251][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:37:29,755][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:37:30,258][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:37:30,762][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:37:31,265][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:37:31,767][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:37:32,273][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:37:32,776][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:37:33,279][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:37:33,781][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:37:34,282][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:37:34,783][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:37:35,284][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:37:35,786][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:37:36,288][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:37:36,790][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:37:37,292][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:37:37,795][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:37:38,298][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:37:38,801][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:37:39,304][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:37:39,806][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:37:40,309][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:37:40,814][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:37:41,319][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:37:41,822][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:37:42,323][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:37:42,825][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:37:43,327][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:37:43,828][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:37:44,331][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:37:44,832][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:37:45,334][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:37:45,840][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:37:46,344][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:37:46,848][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:37:47,352][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:37:47,856][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:37:48,360][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:37:48,866][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:37:49,370][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:37:49,874][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:37:50,377][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:37:50,881][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:37:51,384][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:37:51,888][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:37:52,391][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:37:52,895][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:37:53,399][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:37:53,902][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:37:54,405][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:37:54,908][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:37:55,410][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:37:55,912][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:37:56,414][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:37:56,916][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:37:57,418][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:37:57,921][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:37:58,424][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:37:58,926][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:37:59,433][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:37:59,936][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:38:00,439][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:38:00,942][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:38:01,445][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:38:01,949][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:38:02,452][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:38:02,956][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:38:03,459][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:38:03,962][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:38:04,464][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:38:04,968][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:38:05,471][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:38:05,973][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:38:06,475][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:38:06,976][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:38:07,478][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:38:07,980][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:38:08,482][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:38:08,984][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:38:09,486][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:38:09,988][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:38:10,493][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:38:10,996][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:38:11,500][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:38:12,003][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:38:12,505][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:38:13,009][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:38:13,513][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:38:14,015][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:38:14,517][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:38:15,018][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:38:15,520][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:38:16,022][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:38:16,523][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:38:17,025][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:38:17,527][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:38:18,031][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:38:18,537][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:38:19,042][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:38:19,547][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:38:20,051][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:38:20,555][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:38:21,059][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:38:21,563][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:38:22,067][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:38:22,570][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:38:23,074][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:38:23,578][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:38:24,082][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:38:24,586][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:38:25,090][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:38:25,593][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:38:26,095][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:38:26,596][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:38:27,098][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:38:27,599][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:38:28,101][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:38:28,601][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:38:29,102][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:38:29,603][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-26 01:38:30,224][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-26 01:38:30,961][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:38:30,963][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:38:30,965][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:38:31,746][__main__][INFO] - Iteration 463 took 1m 14s (9.12% Gen, 89.83% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 52h 16m 40s. Estimated total time: 62h 19m 59s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 39s, 500 more iterations: 10h 23m 19s. [2026-03-26 01:38:31,748][__main__][INFO] - Starting iteration 463. [2026-03-26 01:38:32,148][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:38:32,148][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:38:39,056][__main__][INFO] - Number of regex retries in iteration 463: 0 [2026-03-26 01:38:39,057][__main__][INFO] - agents played in iteration 463 are Bob, Alice [2026-03-26 01:38:39,968][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:38:40,555][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:38:41,013][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:38:41,523][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:38:42,024][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:38:42,526][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:38:43,026][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:38:43,526][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:38:44,028][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:38:44,530][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:38:45,031][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:38:45,532][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:38:46,035][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:38:46,536][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:38:47,038][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:38:47,540][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:38:48,041][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:38:48,543][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:38:49,044][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:38:49,545][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:38:50,046][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:38:50,547][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:38:51,048][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:38:51,550][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:38:52,051][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:38:52,552][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:38:53,054][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:38:53,558][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:38:54,061][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:38:54,562][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:38:55,064][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:38:55,566][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:38:56,069][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:38:56,571][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:38:57,072][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:38:57,574][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:38:58,075][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:38:58,577][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:38:59,078][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:38:59,581][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:39:00,082][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:39:00,583][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:39:01,084][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:39:01,584][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:39:02,085][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:39:02,586][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:39:03,086][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:39:03,588][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:39:04,089][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:39:04,590][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:39:05,096][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:39:05,598][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:39:06,100][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:39:06,601][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:39:07,103][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:39:07,604][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:39:08,105][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:39:08,608][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:39:09,109][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:39:09,610][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:39:10,113][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:39:10,615][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:39:11,119][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:39:11,623][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:39:12,125][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:39:12,626][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:39:13,127][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:39:13,629][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:39:14,132][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:39:14,634][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:39:15,136][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:39:15,638][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:39:16,140][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:39:16,642][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:39:17,144][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:39:17,645][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:39:18,146][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:39:18,648][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:39:19,148][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:39:19,650][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:39:20,152][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:39:20,653][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:39:21,154][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:39:21,655][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:39:22,156][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:39:22,657][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:39:23,159][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:39:23,660][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:39:24,161][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:39:24,662][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:39:25,163][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:39:25,665][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:39:26,167][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:39:26,670][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:39:27,172][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:39:27,674][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:39:28,175][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:39:28,677][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:39:29,179][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:39:29,682][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:39:30,183][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:39:30,685][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:39:31,186][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:39:31,688][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:39:32,190][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:39:32,692][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:39:33,193][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:39:33,694][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:39:34,195][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:39:34,696][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:39:35,198][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:39:35,701][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:39:36,202][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:39:36,703][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:39:37,204][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:39:37,705][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:39:38,208][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:39:38,711][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:39:39,214][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:39:39,717][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:39:40,218][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:39:40,721][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:39:41,224][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:39:41,728][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:39:42,229][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:39:42,732][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:39:43,234][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:39:43,737][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:39:44,240][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:39:44,743][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 01:39:45,363][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-26 01:39:46,102][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:39:46,104][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:39:46,106][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:39:46,764][__main__][INFO] - Iteration 464 took 1m 14s (9.26% Gen, 89.86% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 52h 6m 17s. Estimated total time: 62h 10m 50s. Time estimates for 10 more iterations: 12m 26s, 100 more iterations: 2h 4m 21s, 500 more iterations: 10h 21m 48s. [2026-03-26 01:39:46,766][__main__][INFO] - Starting iteration 464. [2026-03-26 01:39:47,165][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:39:47,166][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:39:47,759][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:39:49,282][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:39:54,168][__main__][INFO] - Number of regex retries in iteration 464: 2 [2026-03-26 01:39:54,169][__main__][INFO] - agents played in iteration 464 are Bob, Alice [2026-03-26 01:39:55,081][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:39:55,654][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:39:56,114][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:39:56,621][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:39:57,122][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:39:57,623][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:39:58,125][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:39:58,626][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:39:59,127][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:39:59,629][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:40:00,132][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:40:00,635][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:40:01,138][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:40:01,640][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:40:02,142][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:40:02,644][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:40:03,146][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:40:03,647][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:40:04,149][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:40:04,649][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:40:05,153][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:40:05,656][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:40:06,159][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:40:06,660][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:40:07,162][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:40:07,662][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:40:08,164][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:40:08,664][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:40:09,166][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:40:09,667][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:40:10,168][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:40:10,668][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:40:11,170][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:40:11,674][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:40:12,175][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:40:12,675][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:40:13,175][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:40:13,675][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:40:14,176][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:40:14,676][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:40:15,176][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:40:15,676][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:40:16,177][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:40:16,678][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:40:17,179][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:40:17,681][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:40:18,182][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:40:18,683][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:40:19,184][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:40:19,686][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:40:20,186][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:40:20,687][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:40:21,187][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:40:21,687][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:40:22,187][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:40:22,687][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:40:23,187][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:40:23,687][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:40:24,187][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:40:24,688][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:40:25,190][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:40:25,692][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:40:26,194][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:40:26,695][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:40:27,196][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:40:27,697][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:40:28,199][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:40:28,700][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:40:29,205][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:40:29,704][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:40:30,205][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:40:30,707][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:40:31,208][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:40:31,710][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:40:32,212][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:40:32,715][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:40:33,216][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:40:33,720][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:40:34,223][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:40:34,725][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:40:35,226][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:40:35,728][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:40:36,232][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:40:36,734][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:40:37,236][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:40:37,738][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:40:38,240][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:40:38,742][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:40:39,244][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:40:39,745][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:40:40,247][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:40:40,748][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:40:41,251][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:40:41,755][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:40:42,256][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:40:42,758][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:40:43,259][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:40:43,762][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:40:44,262][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:40:44,762][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:40:45,262][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:40:45,762][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:40:46,263][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:40:46,763][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:40:47,263][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:40:47,763][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:40:48,264][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:40:48,765][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:40:49,267][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:40:49,769][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:40:50,270][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:40:50,771][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:40:51,272][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:40:51,774][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:40:52,276][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:40:52,777][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:40:53,278][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:40:53,779][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:40:54,280][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:40:54,781][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:40:55,282][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:40:55,783][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:40:56,284][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:40:56,787][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:40:57,288][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:40:57,790][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:40:58,293][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:40:58,794][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:40:59,295][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:40:59,796][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 01:41:00,422][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-26 01:41:01,171][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:41:01,174][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:41:01,175][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:41:02,036][__main__][INFO] - Iteration 465 took 1m 14s (9.35% Gen, 89.49% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 17m 45s. Estimated total time: 62h 23m 34s. Time estimates for 10 more iterations: 12m 28s, 100 more iterations: 2h 4m 47s, 500 more iterations: 10h 23m 55s. [2026-03-26 01:41:02,038][__main__][INFO] - Starting iteration 465. [2026-03-26 01:41:02,437][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:41:02,437][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:41:03,634][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:41:10,114][__main__][INFO] - Number of regex retries in iteration 465: 1 [2026-03-26 01:41:10,115][__main__][INFO] - agents played in iteration 465 are Bob, Alice [2026-03-26 01:41:11,021][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:41:11,604][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:41:12,061][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:41:12,568][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:41:13,071][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:41:13,573][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:41:14,075][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:41:14,578][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:41:15,079][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:41:15,581][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:41:16,082][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:41:16,582][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:41:17,083][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:41:17,584][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:41:18,084][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:41:18,584][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:41:19,085][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:41:19,585][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:41:20,086][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:41:20,586][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:41:21,086][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:41:21,587][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:41:22,087][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:41:22,587][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:41:23,088][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:41:23,587][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:41:24,089][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:41:24,589][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:41:25,092][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:41:25,594][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:41:26,095][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:41:26,596][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:41:27,098][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:41:27,599][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:41:28,099][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:41:28,600][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:41:29,101][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:41:29,602][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:41:30,103][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:41:30,603][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:41:31,103][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:41:31,603][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:41:32,106][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:41:32,609][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:41:33,113][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:41:33,617][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:41:34,120][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:41:34,623][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:41:35,126][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:41:35,627][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:41:36,128][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:41:36,629][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:41:37,133][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:41:37,634][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:41:38,135][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:41:38,636][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:41:39,138][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:41:39,639][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:41:40,140][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:41:40,642][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:41:41,145][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:41:41,648][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:41:42,149][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:41:42,650][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:41:43,153][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:41:43,654][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:41:44,156][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:41:44,658][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:41:45,160][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:41:45,660][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:41:46,162][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:41:46,662][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:41:47,164][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:41:47,666][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:41:48,166][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:41:48,665][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:41:49,164][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:41:49,664][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:41:50,163][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:41:50,664][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:41:51,164][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:41:51,664][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:41:52,163][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:41:52,663][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:41:53,163][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:41:53,663][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:41:54,163][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:41:54,664][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:41:55,164][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:41:55,664][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:41:56,164][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:41:56,665][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:41:57,165][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:41:57,667][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:41:58,168][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:41:58,671][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:41:59,171][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:41:59,674][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:42:00,175][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:42:00,676][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:42:01,176][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:42:01,677][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:42:02,177][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:42:02,677][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:42:03,177][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:42:03,678][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:42:04,182][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:42:04,684][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:42:05,186][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:42:05,688][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:42:06,191][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:42:06,694][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:42:07,195][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:42:07,698][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:42:08,198][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:42:08,700][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:42:09,201][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:42:09,703][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:42:10,203][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:42:10,705][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:42:11,205][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:42:11,708][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:42:12,212][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:42:12,713][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:42:13,215][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:42:13,717][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:42:14,218][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:42:14,720][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:42:15,222][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:42:15,724][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21749 tokens. [2026-03-26 01:42:16,339][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-26 01:42:17,078][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:42:17,080][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:42:17,081][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:42:17,735][__main__][INFO] - Iteration 466 took 1m 15s (10.20% Gen, 88.93% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 52h 37m 51s. Estimated total time: 62h 44m 55s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 29s, 500 more iterations: 10h 27m 29s. [2026-03-26 01:42:17,740][__main__][INFO] - Starting iteration 466. [2026-03-26 01:42:18,141][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:42:18,142][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:42:25,424][__main__][INFO] - Number of regex retries in iteration 466: 0 [2026-03-26 01:42:25,425][__main__][INFO] - agents played in iteration 466 are Bob, Alice [2026-03-26 01:42:26,329][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:42:26,913][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:42:27,370][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:42:27,875][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:42:28,376][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:42:28,877][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:42:29,378][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:42:29,880][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:42:30,380][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:42:30,881][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:42:31,381][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:42:31,881][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:42:32,381][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:42:32,881][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:42:33,381][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:42:33,881][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:42:34,381][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:42:34,881][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:42:35,385][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:42:35,887][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:42:36,389][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:42:36,890][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:42:37,392][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:42:37,895][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:42:38,397][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:42:38,899][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:42:39,402][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:42:39,903][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:42:40,405][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:42:40,907][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:42:41,412][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:42:41,915][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:42:42,418][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:42:42,920][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:42:43,421][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:42:43,921][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:42:44,422][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:42:44,922][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:42:45,422][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:42:45,921][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:42:46,421][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:42:46,922][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:42:47,426][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:42:47,930][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:42:48,433][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:42:48,937][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:42:49,440][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:42:49,942][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:42:50,445][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:42:50,947][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:42:51,449][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:42:51,952][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:42:52,456][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:42:52,959][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:42:53,462][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:42:53,965][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:42:54,468][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:42:54,972][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:42:55,475][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:42:55,977][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:42:56,479][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:42:56,981][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:42:57,482][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:42:57,984][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:42:58,486][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:42:58,989][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:42:59,491][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:42:59,992][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:43:00,493][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:43:00,995][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:43:01,496][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:43:01,997][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:43:02,498][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:43:02,999][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:43:03,499][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:43:03,999][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:43:04,499][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:43:04,999][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:43:05,499][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:43:05,999][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:43:06,499][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:43:06,998][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:43:07,502][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:43:08,004][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:43:08,508][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:43:09,010][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:43:09,512][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:43:10,015][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:43:10,517][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:43:11,020][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:43:11,524][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:43:12,026][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:43:12,529][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:43:13,035][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:43:13,537][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:43:14,039][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:43:14,541][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:43:15,043][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:43:15,545][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:43:16,046][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:43:16,548][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:43:17,051][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:43:17,552][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:43:18,053][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:43:18,554][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:43:19,056][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:43:19,559][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:43:20,062][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:43:20,565][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:43:21,067][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:43:21,569][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:43:22,073][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:43:22,576][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:43:23,078][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:43:23,580][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:43:24,083][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:43:24,585][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:43:25,088][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:43:25,590][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:43:26,092][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:43:26,594][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:43:27,098][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:43:27,601][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:43:28,102][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:43:28,604][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:43:29,105][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:43:29,607][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:43:30,110][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:43:30,615][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:43:31,117][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-26 01:43:31,738][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.29%, ΔTime: 00:01:04 [2026-03-26 01:43:32,476][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:43:32,479][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:43:32,480][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:43:33,178][__main__][INFO] - Iteration 467 took 1m 15s (9.71% Gen, 89.36% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 23m 33s. Estimated total time: 62h 31m 53s. Time estimates for 10 more iterations: 12m 30s, 100 more iterations: 2h 5m 3s, 500 more iterations: 10h 25m 18s. [2026-03-26 01:43:33,180][__main__][INFO] - Starting iteration 467. [2026-03-26 01:43:33,581][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:43:33,581][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:43:34,170][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:43:35,857][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:43:40,887][__main__][INFO] - Number of regex retries in iteration 467: 2 [2026-03-26 01:43:40,888][__main__][INFO] - agents played in iteration 467 are Bob, Alice [2026-03-26 01:43:41,799][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:43:42,385][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:43:42,842][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:43:43,348][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:43:43,850][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:43:44,352][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:43:44,853][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:43:45,355][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:43:45,856][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:43:46,357][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:43:46,860][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:43:47,360][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:43:47,862][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:43:48,363][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:43:48,866][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:43:49,367][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:43:49,868][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:43:50,370][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:43:50,874][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:43:51,377][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:43:51,880][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:43:52,382][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:43:52,884][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:43:53,386][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:43:53,889][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:43:54,390][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:43:54,895][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:43:55,397][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:43:55,899][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:43:56,401][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:43:56,903][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:43:57,404][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:43:57,905][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:43:58,408][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:43:58,930][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:43:59,437][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:43:59,941][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:44:00,446][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:44:00,950][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:44:01,453][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:44:01,957][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:44:02,460][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:44:02,963][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:44:03,466][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:44:03,969][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:44:04,473][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:44:04,976][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:44:05,480][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:44:05,983][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:44:06,486][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:44:06,987][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:44:07,489][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:44:07,992][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:44:08,494][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:44:08,996][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:44:09,498][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:44:10,000][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:44:10,501][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:44:11,005][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:44:11,510][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:44:12,014][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:44:12,518][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:44:13,022][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:44:13,525][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:44:14,029][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:44:14,532][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:44:15,035][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:44:15,536][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:44:16,037][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:44:16,540][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:44:17,042][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:44:17,544][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:44:18,044][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:44:18,545][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:44:19,048][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:44:19,551][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:44:20,053][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:44:20,554][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:44:21,056][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:44:21,557][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:44:22,060][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:44:22,562][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:44:23,065][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:44:23,567][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:44:24,069][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:44:24,572][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:44:25,074][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:44:25,577][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:44:26,079][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:44:26,581][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:44:27,082][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:44:27,584][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:44:28,086][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:44:28,588][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:44:29,091][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:44:29,592][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:44:30,094][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:44:30,597][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:44:31,102][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:44:31,605][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:44:32,108][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:44:32,611][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:44:33,116][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:44:33,620][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:44:34,123][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:44:34,627][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:44:35,130][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:44:35,636][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:44:36,140][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:44:36,644][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:44:37,147][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:44:37,650][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:44:38,155][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:44:38,658][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:44:39,160][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:44:39,662][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:44:40,164][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:44:40,665][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:44:41,168][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:44:41,672][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:44:42,173][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:44:42,675][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:44:43,178][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:44:43,681][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:44:44,184][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:44:44,687][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:44:45,191][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:44:45,694][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:44:46,197][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:44:46,701][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21730 tokens. [2026-03-26 01:44:47,317][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.66%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:04 [2026-03-26 01:44:48,055][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:44:48,058][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:44:48,059][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:44:48,713][__main__][INFO] - Iteration 468 took 1m 15s (9.73% Gen, 89.40% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 27m 2s. Estimated total time: 62h 36m 38s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 13s, 500 more iterations: 10h 26m 6s. [2026-03-26 01:44:48,715][__main__][INFO] - Starting iteration 468. [2026-03-26 01:44:49,113][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:44:49,114][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:44:49,712][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:44:52,109][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:44:55,254][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:44:56,390][__main__][INFO] - Number of regex retries in iteration 468: 3 [2026-03-26 01:44:56,391][__main__][INFO] - agents played in iteration 468 are Bob, Alice [2026-03-26 01:44:57,299][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:44:57,890][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:44:58,346][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:44:58,852][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:44:59,354][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:44:59,856][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:45:00,357][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:45:00,860][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:45:01,361][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:45:01,862][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:45:02,361][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:45:02,861][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:45:03,362][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:45:03,862][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:45:04,363][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:45:04,863][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:45:05,363][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:45:05,863][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:45:06,365][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:45:06,866][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:45:07,366][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:45:07,868][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:45:08,369][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:45:08,869][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:45:09,373][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:45:09,874][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:45:10,377][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:45:10,877][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:45:11,378][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:45:11,879][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:45:12,379][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:45:12,879][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:45:13,379][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:45:13,879][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:45:14,380][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:45:14,881][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:45:15,381][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:45:15,882][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:45:16,382][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:45:16,882][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:45:17,382][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:45:17,883][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:45:18,387][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:45:18,890][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:45:19,393][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:45:19,895][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:45:20,397][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:45:20,899][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:45:21,401][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:45:21,903][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:45:22,403][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:45:22,904][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:45:23,405][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:45:23,905][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:45:24,405][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:45:24,905][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:45:25,405][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:45:25,906][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:45:26,408][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:45:26,909][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:45:27,411][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:45:27,914][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:45:28,415][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:45:28,917][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:45:29,419][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:45:29,922][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:45:30,422][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:45:30,923][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:45:31,425][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:45:31,927][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:45:32,428][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:45:32,930][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:45:33,431][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:45:33,933][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:45:34,433][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:45:34,934][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:45:35,434][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:45:35,934][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:45:36,435][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:45:36,936][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:45:37,436][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:45:37,936][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:45:38,436][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:45:38,937][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:45:39,438][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:45:39,940][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:45:40,441][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:45:40,942][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:45:41,443][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:45:41,944][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:45:42,445][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:45:42,946][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:45:43,446][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:45:43,947][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:45:44,449][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:45:44,951][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:45:45,451][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:45:45,951][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:45:46,452][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:45:46,953][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:45:47,454][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:45:47,955][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:45:48,457][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:45:48,957][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:45:49,458][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:45:49,959][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:45:50,461][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:45:50,963][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:45:51,465][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:45:51,967][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:45:52,469][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:45:52,970][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:45:53,474][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:45:53,976][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:45:54,476][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:45:54,978][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:45:55,478][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:45:55,978][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:45:56,479][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:45:56,979][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:45:57,480][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:45:57,980][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:45:58,482][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:45:59,005][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:45:59,512][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:46:00,013][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:46:00,515][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:46:01,017][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:46:01,519][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:46:02,024][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21744 tokens. [2026-03-26 01:46:02,645][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 01:46:03,387][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:46:03,389][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:46:03,391][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:46:04,039][__main__][INFO] - Iteration 469 took 1m 14s (9.71% Gen, 89.42% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 52h 15m 27s. Estimated total time: 62h 26m 18s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 52s, 500 more iterations: 10h 24m 23s. [2026-03-26 01:46:04,041][__main__][INFO] - Starting iteration 469. [2026-03-26 01:46:04,438][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:46:04,439][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:46:11,686][__main__][INFO] - Number of regex retries in iteration 469: 0 [2026-03-26 01:46:11,687][__main__][INFO] - agents played in iteration 469 are Bob, Alice [2026-03-26 01:46:12,590][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:46:13,172][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:46:13,630][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:46:14,138][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:46:14,641][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:46:15,143][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:46:15,646][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:46:16,150][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:46:16,655][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:46:17,158][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:46:17,661][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:46:18,165][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:46:18,667][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:46:19,169][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:46:19,672][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:46:20,175][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:46:20,679][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:46:21,180][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:46:21,681][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:46:22,182][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:46:22,683][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:46:23,184][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:46:23,686][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:46:24,186][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:46:24,687][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:46:25,188][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:46:25,689][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:46:26,189][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:46:26,688][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:46:27,189][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:46:27,689][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:46:28,191][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:46:28,692][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:46:29,193][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:46:29,695][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:46:30,196][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:46:30,698][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:46:31,200][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:46:31,701][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:46:32,203][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:46:32,704][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:46:33,205][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:46:33,708][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:46:34,212][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:46:34,714][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:46:35,217][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:46:35,720][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:46:36,221][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:46:36,723][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:46:37,225][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:46:37,726][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:46:38,228][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:46:38,729][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:46:39,231][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:46:39,734][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:46:40,235][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:46:40,737][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:46:41,240][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:46:41,743][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:46:42,245][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:46:42,746][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:46:43,249][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:46:43,752][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:46:44,254][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:46:44,756][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:46:45,259][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:46:45,762][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:46:46,264][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:46:46,768][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:46:47,270][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:46:47,773][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:46:48,276][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:46:48,779][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:46:49,282][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:46:49,784][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:46:50,286][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:46:50,788][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:46:51,291][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:46:51,794][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:46:52,295][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:46:52,797][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:46:53,300][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:46:53,800][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:46:54,301][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:46:54,803][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:46:55,304][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:46:55,805][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:46:56,305][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:46:56,805][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:46:57,306][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:46:57,807][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:46:58,308][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:46:58,808][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:46:59,309][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:46:59,810][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:47:00,310][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:47:00,814][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:47:01,316][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:47:01,817][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:47:02,318][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:47:02,819][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:47:03,322][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:47:03,822][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:47:04,323][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:47:04,824][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:47:05,325][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:47:05,826][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:47:06,328][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:47:06,831][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:47:07,333][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:47:07,836][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:47:08,338][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:47:08,840][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:47:09,343][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:47:09,844][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:47:10,345][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:47:10,847][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:47:11,350][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:47:11,852][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:47:12,353][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:47:12,855][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:47:13,357][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:47:13,859][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:47:14,361][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:47:14,864][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:47:15,366][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:47:15,868][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:47:16,370][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:47:16,872][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:47:17,373][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-26 01:47:17,986][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 01:47:18,719][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:47:18,721][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:47:18,723][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:47:19,543][__main__][INFO] - Iteration 470 took 1m 15s (9.65% Gen, 89.26% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 23m 8s. Estimated total time: 62h 35m 15s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 10s, 500 more iterations: 10h 25m 52s. [2026-03-26 01:47:19,547][__main__][INFO] - Starting iteration 470. [2026-03-26 01:47:19,944][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:47:19,945][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:47:26,844][__main__][INFO] - Number of regex retries in iteration 470: 0 [2026-03-26 01:47:26,844][__main__][INFO] - agents played in iteration 470 are Bob, Alice [2026-03-26 01:47:27,753][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:47:28,332][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:47:28,791][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:47:29,298][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:47:29,802][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:47:30,304][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:47:30,806][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:47:31,309][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:47:31,811][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:47:32,316][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:47:32,818][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:47:33,321][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:47:33,823][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:47:34,324][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:47:34,826][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:47:35,329][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:47:35,832][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:47:36,335][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:47:36,836][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:47:37,337][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:47:37,837][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:47:38,337][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:47:38,838][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:47:39,339][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:47:39,839][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:47:40,340][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:47:40,841][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:47:41,344][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:47:41,845][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:47:42,346][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:47:42,847][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:47:43,348][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:47:43,848][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:47:44,350][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:47:44,853][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:47:45,356][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:47:45,858][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:47:46,361][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:47:46,863][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:47:47,364][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:47:47,866][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:47:48,368][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:47:48,871][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:47:49,372][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:47:49,874][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:47:50,376][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:47:50,878][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:47:51,382][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:47:51,883][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:47:52,384][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:47:52,885][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:47:53,387][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:47:53,889][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:47:54,390][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:47:54,892][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:47:55,393][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:47:55,894][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:47:56,396][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:47:56,898][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:47:57,400][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:47:57,902][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:47:58,403][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:47:58,903][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:47:59,405][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:47:59,906][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:48:00,408][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:48:00,910][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:48:01,414][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:48:01,916][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:48:02,419][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:48:02,923][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:48:03,426][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:48:03,928][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:48:04,431][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:48:04,937][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:48:05,439][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:48:05,941][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:48:06,443][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:48:06,944][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:48:07,445][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:48:07,947][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:48:08,449][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:48:08,951][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:48:09,451][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:48:09,951][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:48:10,452][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:48:10,953][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:48:11,457][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:48:11,958][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:48:12,459][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:48:12,961][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:48:13,462][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:48:13,964][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:48:14,465][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:48:14,966][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:48:15,468][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:48:15,970][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:48:16,471][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:48:16,973][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:48:17,475][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:48:17,977][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:48:18,478][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:48:18,980][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:48:19,482][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:48:19,983][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:48:20,484][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:48:20,985][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:48:21,486][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:48:21,988][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:48:22,488][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:48:22,989][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:48:23,492][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:48:23,993][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:48:24,494][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:48:24,997][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:48:25,498][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:48:26,000][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:48:26,503][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:48:27,005][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:48:27,506][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:48:28,008][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:48:28,509][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:48:29,013][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:48:29,516][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:48:30,018][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:48:30,520][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:48:31,022][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:48:31,523][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:48:32,026][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:48:32,528][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-26 01:48:33,140][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:04 [2026-03-26 01:48:33,880][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:48:33,883][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:48:33,884][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:48:34,716][__main__][INFO] - Iteration 471 took 1m 14s (9.23% Gen, 89.66% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 52h 5m 16s. Estimated total time: 62h 18m 37s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 37s, 500 more iterations: 10h 23m 6s. [2026-03-26 01:48:34,718][__main__][INFO] - Starting iteration 471. [2026-03-26 01:48:35,118][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:48:35,119][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:48:42,083][__main__][INFO] - Number of regex retries in iteration 471: 0 [2026-03-26 01:48:42,084][__main__][INFO] - agents played in iteration 471 are Bob, Alice [2026-03-26 01:48:42,991][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:48:43,570][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:48:44,028][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:48:44,534][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:48:45,037][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:48:45,540][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:48:46,042][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:48:46,543][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:48:47,045][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:48:47,546][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:48:48,050][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:48:48,554][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:48:49,057][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:48:49,560][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:48:50,063][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:48:50,564][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:48:51,066][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:48:51,569][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:48:52,071][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:48:52,572][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:48:53,075][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:48:53,578][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:48:54,080][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:48:54,583][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:48:55,085][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:48:55,587][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:48:56,087][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:48:56,589][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:48:57,091][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:48:57,593][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:48:58,095][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:48:58,596][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:48:59,097][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:48:59,599][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:49:00,104][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:49:00,607][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:49:01,110][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:49:01,613][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:49:02,117][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:49:02,620][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:49:03,124][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:49:03,627][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:49:04,129][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:49:04,633][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:49:05,137][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:49:05,640][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:49:06,143][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:49:06,645][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:49:07,147][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:49:07,649][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:49:08,151][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:49:08,653][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:49:09,155][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:49:09,656][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:49:10,158][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:49:10,659][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:49:11,161][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:49:11,664][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:49:12,165][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:49:12,665][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:49:13,165][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:49:13,665][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:49:14,166][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:49:14,666][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:49:15,167][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:49:15,667][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:49:16,168][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:49:16,668][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:49:17,168][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:49:17,669][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:49:18,170][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:49:18,672][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:49:19,173][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:49:19,675][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:49:20,177][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:49:20,679][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:49:21,182][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:49:21,683][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:49:22,185][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:49:22,687][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:49:23,189][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:49:23,693][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:49:24,195][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:49:24,697][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:49:25,199][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:49:25,700][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:49:26,203][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:49:26,705][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:49:27,207][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:49:27,708][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:49:28,210][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:49:28,713][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:49:29,216][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:49:29,717][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:49:30,220][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:49:30,721][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:49:31,223][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:49:31,726][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:49:32,229][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:49:32,733][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:49:33,236][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:49:33,740][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:49:34,243][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:49:34,746][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:49:35,249][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:49:35,752][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:49:36,254][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:49:36,757][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:49:37,260][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:49:37,763][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:49:38,266][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:49:38,768][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:49:39,270][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:49:39,771][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:49:40,274][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:49:40,774][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:49:41,276][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:49:41,778][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:49:42,278][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:49:42,779][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:49:43,280][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:49:43,781][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:49:44,283][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:49:44,783][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:49:45,285][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:49:45,785][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:49:46,286][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:49:46,786][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:49:47,287][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:49:47,788][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21750 tokens. [2026-03-26 01:49:48,400][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:04 [2026-03-26 01:49:49,138][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:49:49,140][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:49:49,142][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:49:49,788][__main__][INFO] - Iteration 472 took 1m 14s (9.33% Gen, 89.80% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 58m 54s. Estimated total time: 62h 13m 31s. Time estimates for 10 more iterations: 12m 26s, 100 more iterations: 2h 4m 27s, 500 more iterations: 10h 22m 15s. [2026-03-26 01:49:49,790][__main__][INFO] - Starting iteration 472. [2026-03-26 01:49:50,190][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:49:50,191][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:49:57,104][__main__][INFO] - Number of regex retries in iteration 472: 0 [2026-03-26 01:49:57,104][__main__][INFO] - agents played in iteration 472 are Bob, Alice [2026-03-26 01:49:58,011][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:49:58,590][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:49:59,049][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:49:59,556][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:50:00,058][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:50:00,561][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:50:01,063][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:50:01,565][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:50:02,068][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:50:02,570][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:50:03,071][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:50:03,573][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:50:04,075][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:50:04,577][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:50:05,078][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:50:05,579][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:50:06,080][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:50:06,581][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:50:07,084][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:50:07,586][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:50:08,087][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:50:08,588][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:50:09,090][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:50:09,590][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:50:10,093][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:50:10,595][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:50:11,097][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:50:11,600][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:50:12,102][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:50:12,603][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:50:13,104][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:50:13,605][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:50:14,106][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:50:14,608][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:50:15,108][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:50:15,609][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:50:16,115][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:50:16,616][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:50:17,118][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:50:17,619][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:50:18,120][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:50:18,621][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:50:19,122][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:50:19,624][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:50:20,126][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:50:20,628][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:50:21,129][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:50:21,631][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:50:22,135][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:50:22,638][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:50:23,142][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:50:23,645][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:50:24,146][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:50:24,649][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:50:25,153][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:50:25,656][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:50:26,159][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:50:26,662][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:50:27,163][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:50:27,665][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:50:28,166][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:50:28,668][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:50:29,169][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:50:29,671][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:50:30,171][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:50:30,675][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:50:31,178][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:50:31,680][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:50:32,182][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:50:32,684][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:50:33,186][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:50:33,688][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:50:34,191][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:50:34,694][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:50:35,195][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:50:35,696][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:50:36,198][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:50:36,700][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:50:37,201][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:50:37,702][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:50:38,203][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:50:38,704][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:50:39,204][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:50:39,705][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:50:40,206][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:50:40,708][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:50:41,210][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:50:41,713][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:50:42,215][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:50:42,716][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:50:43,219][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:50:43,721][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:50:44,222][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:50:44,723][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:50:45,224][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:50:45,725][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:50:46,226][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:50:46,728][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:50:47,229][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:50:47,730][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:50:48,232][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:50:48,736][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:50:49,237][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:50:49,739][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:50:50,240][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:50:50,742][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:50:51,243][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:50:51,746][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:50:52,248][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:50:52,750][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:50:53,251][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:50:53,752][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:50:54,254][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:50:54,755][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:50:55,257][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:50:55,760][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:50:56,263][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:50:56,765][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:50:57,268][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:50:57,770][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:50:58,274][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:50:58,777][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:50:59,278][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:50:59,780][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:51:00,282][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:51:00,783][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:51:01,284][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:51:01,786][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:51:02,288][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:51:02,788][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-26 01:51:03,397][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-26 01:51:04,129][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:51:04,131][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:51:04,133][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:51:04,996][__main__][INFO] - Iteration 473 took 1m 14s (9.24% Gen, 89.60% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 52h 4m 26s. Estimated total time: 62h 20m 18s. Time estimates for 10 more iterations: 12m 28s, 100 more iterations: 2h 4m 40s, 500 more iterations: 10h 23m 23s. [2026-03-26 01:51:04,998][__main__][INFO] - Starting iteration 473. [2026-03-26 01:51:05,397][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:51:05,397][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:51:13,074][__main__][INFO] - Number of regex retries in iteration 473: 0 [2026-03-26 01:51:13,075][__main__][INFO] - agents played in iteration 473 are Bob, Alice [2026-03-26 01:51:13,980][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:51:14,555][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:51:15,012][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:51:15,519][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:51:16,021][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:51:16,523][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:51:17,025][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:51:17,527][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:51:18,027][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:51:18,528][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:51:19,028][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:51:19,529][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:51:20,029][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:51:20,530][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:51:21,031][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:51:21,532][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:51:22,032][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:51:22,535][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:51:23,036][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:51:23,536][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:51:24,037][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:51:24,538][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:51:25,039][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:51:25,540][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:51:26,041][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:51:26,543][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:51:27,047][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:51:27,549][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:51:28,051][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:51:28,555][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:51:29,057][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:51:29,560][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:51:30,062][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:51:30,564][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:51:31,066][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:51:31,568][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:51:32,071][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:51:32,573][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:51:33,076][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:51:33,578][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:51:34,080][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:51:34,583][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:51:35,083][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:51:35,582][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:51:36,083][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:51:36,582][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:51:37,082][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:51:37,582][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:51:38,082][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:51:38,582][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:51:39,083][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:51:39,585][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:51:40,087][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:51:40,587][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:51:41,090][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:51:41,594][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:51:42,096][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:51:42,598][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:51:43,099][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:51:43,599][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:51:44,101][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:51:44,602][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:51:45,103][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:51:45,604][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:51:46,105][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:51:46,605][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:51:47,105][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:51:47,605][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:51:48,106][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:51:48,606][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:51:49,107][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:51:49,608][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:51:50,108][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:51:50,610][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:51:51,111][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:51:51,611][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:51:52,112][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:51:52,611][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:51:53,111][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:51:53,611][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:51:54,113][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:51:54,614][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:51:55,114][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:51:55,614][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:51:56,115][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:51:56,617][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:51:57,117][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:51:57,617][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:51:58,117][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:51:58,618][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:51:59,120][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:51:59,623][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:52:00,124][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:52:00,627][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:52:01,129][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:52:01,632][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:52:02,135][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:52:02,637][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:52:03,140][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:52:03,642][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:52:04,144][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:52:04,647][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:52:05,149][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:52:05,650][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:52:06,153][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:52:06,655][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:52:07,155][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:52:07,656][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:52:08,156][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:52:08,656][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:52:09,156][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:52:09,657][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:52:10,158][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:52:10,658][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:52:11,160][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:52:11,661][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:52:12,162][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:52:12,663][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:52:13,163][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:52:13,666][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:52:14,167][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:52:14,668][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:52:15,169][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:52:15,670][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:52:16,172][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:52:16,673][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:52:17,175][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:52:17,676][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:52:18,177][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:52:18,678][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21746 tokens. [2026-03-26 01:52:19,288][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-26 01:52:20,022][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:52:20,025][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:52:20,026][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:52:20,677][__main__][INFO] - Iteration 474 took 1m 15s (10.20% Gen, 88.93% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 52h 26m 57s. Estimated total time: 62h 44m 4s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 28s, 500 more iterations: 10h 27m 20s. [2026-03-26 01:52:20,679][__main__][INFO] - Starting iteration 474. [2026-03-26 01:52:21,079][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:52:21,079][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:52:27,928][__main__][INFO] - Number of regex retries in iteration 474: 0 [2026-03-26 01:52:27,929][__main__][INFO] - agents played in iteration 474 are Bob, Alice [2026-03-26 01:52:28,838][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:52:29,416][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:52:29,874][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:52:30,381][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:52:30,883][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:52:31,385][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:52:31,887][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:52:32,388][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:52:32,890][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:52:33,393][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:52:33,895][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:52:34,397][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:52:34,899][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:52:35,400][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:52:35,902][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:52:36,404][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:52:36,906][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:52:37,407][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:52:37,907][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:52:38,407][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:52:38,907][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:52:39,409][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:52:39,912][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:52:40,412][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:52:40,912][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:52:41,416][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:52:41,918][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:52:42,420][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:52:42,922][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:52:43,423][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:52:43,925][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:52:44,426][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:52:44,928][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:52:45,429][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:52:45,931][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:52:46,434][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:52:46,936][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:52:47,438][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:52:47,939][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:52:48,442][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:52:48,944][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:52:49,445][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:52:49,946][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:52:50,447][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:52:50,947][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:52:51,450][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:52:51,952][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:52:52,453][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:52:52,954][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:52:53,455][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:52:53,958][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:52:54,459][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:52:54,962][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:52:55,464][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:52:55,965][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:52:56,467][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:52:56,968][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:52:57,470][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:52:57,975][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:52:58,478][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:52:58,981][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:52:59,484][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:52:59,986][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:53:00,490][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:53:00,993][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:53:01,496][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:53:01,998][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:53:02,500][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:53:03,002][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:53:03,504][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:53:04,006][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:53:04,507][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:53:05,009][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:53:05,513][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:53:06,015][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:53:06,517][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:53:07,018][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:53:07,520][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:53:08,021][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:53:08,523][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:53:09,024][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:53:09,526][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:53:10,027][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:53:10,528][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:53:11,029][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:53:11,535][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:53:12,037][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:53:12,539][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:53:13,041][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:53:13,543][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:53:14,044][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:53:14,547][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:53:15,049][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:53:15,552][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:53:16,053][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:53:16,555][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:53:17,057][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:53:17,559][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:53:18,060][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:53:18,561][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:53:19,062][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:53:19,562][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:53:20,063][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:53:20,563][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:53:21,063][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:53:21,564][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:53:22,065][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:53:22,565][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:53:23,066][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:53:23,567][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:53:24,068][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:53:24,569][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:53:25,070][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:53:25,571][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:53:26,072][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:53:26,573][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:53:27,076][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:53:27,577][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:53:28,079][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:53:28,581][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:53:29,082][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:53:29,584][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:53:30,086][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:53:30,589][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:53:31,092][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:53:31,596][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:53:32,098][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:53:32,601][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:53:33,104][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:53:33,608][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 01:53:34,218][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-26 01:53:34,953][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:53:34,956][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:53:34,957][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:53:35,808][__main__][INFO] - Iteration 475 took 1m 14s (9.17% Gen, 89.69% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 58m 7s. Estimated total time: 62h 16m 29s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 32s, 500 more iterations: 10h 22m 44s. [2026-03-26 01:53:35,810][__main__][INFO] - Starting iteration 475. [2026-03-26 01:53:36,210][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:53:36,211][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:53:39,644][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:53:43,379][__main__][INFO] - Number of regex retries in iteration 475: 1 [2026-03-26 01:53:43,379][__main__][INFO] - agents played in iteration 475 are Bob, Alice [2026-03-26 01:53:44,290][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:53:44,871][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:53:45,326][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:53:45,829][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:53:46,328][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:53:46,825][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:53:47,324][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:53:47,822][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:53:48,319][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:53:48,818][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:53:49,321][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:53:49,823][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:53:50,326][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:53:50,828][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:53:51,329][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:53:51,830][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:53:52,333][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:53:52,836][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:53:53,338][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:53:53,841][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:53:54,343][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:53:54,845][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:53:55,347][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:53:55,850][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:53:56,353][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:53:56,855][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:53:57,357][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:53:57,859][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:53:58,361][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:53:58,862][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:53:59,364][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:53:59,865][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:54:00,366][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:54:00,868][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:54:01,390][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:54:01,896][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:54:02,399][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:54:02,901][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:54:03,403][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:54:03,906][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:54:04,408][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:54:04,910][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:54:05,413][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:54:05,915][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:54:06,418][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:54:06,922][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:54:07,424][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:54:07,926][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:54:08,429][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:54:08,933][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:54:09,436][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:54:09,939][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:54:10,441][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:54:10,943][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:54:11,448][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:54:11,951][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:54:12,455][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:54:12,958][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:54:13,460][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:54:13,961][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:54:14,463][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:54:14,965][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:54:15,467][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:54:15,969][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:54:16,471][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:54:16,972][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:54:17,471][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:54:17,970][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:54:18,469][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:54:18,967][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:54:19,466][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:54:19,964][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:54:20,462][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:54:20,961][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:54:21,463][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:54:21,965][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:54:22,467][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:54:22,968][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:54:23,470][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:54:23,971][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:54:24,474][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:54:24,976][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:54:25,478][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:54:25,980][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:54:26,481][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:54:26,983][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:54:27,484][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:54:27,986][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:54:28,488][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:54:28,989][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:54:29,491][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:54:29,992][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:54:30,494][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:54:30,996][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:54:31,498][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:54:32,000][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:54:32,501][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:54:33,002][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:54:33,505][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:54:34,007][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:54:34,510][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:54:35,012][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:54:35,516][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:54:36,018][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:54:36,522][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:54:37,025][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:54:37,527][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:54:38,029][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:54:38,533][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:54:39,036][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:54:39,539][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:54:40,042][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:54:40,544][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:54:41,046][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:54:41,551][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:54:42,054][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:54:42,557][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:54:43,060][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:54:43,563][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:54:44,065][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:54:44,567][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:54:45,070][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:54:45,573][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:54:46,074][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:54:46,577][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:54:47,079][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:54:47,581][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:54:48,084][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:54:48,586][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:54:49,088][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-26 01:54:49,701][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.27%, ΔTime: 00:01:04 [2026-03-26 01:54:50,443][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:54:50,445][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:54:50,446][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:54:51,148][__main__][INFO] - Iteration 476 took 1m 14s (9.57% Gen, 89.50% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 7m 16s. Estimated total time: 62h 26m 54s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 53s, 500 more iterations: 10h 24m 29s. [2026-03-26 01:54:51,150][__main__][INFO] - Starting iteration 476. [2026-03-26 01:54:51,549][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:54:51,549][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:54:58,157][__main__][INFO] - Number of regex retries in iteration 476: 0 [2026-03-26 01:54:58,158][__main__][INFO] - agents played in iteration 476 are Bob, Alice [2026-03-26 01:54:59,066][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:54:59,645][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:55:00,105][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:55:00,611][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:55:01,115][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:55:01,617][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:55:02,120][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:55:02,621][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:55:03,125][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:55:03,627][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:55:04,129][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:55:04,630][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:55:05,132][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:55:05,636][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:55:06,138][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:55:06,640][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:55:07,142][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:55:07,643][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:55:08,149][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:55:08,654][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:55:09,159][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:55:09,664][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:55:10,167][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:55:10,672][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:55:11,176][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:55:11,682][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:55:12,185][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:55:12,686][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:55:13,189][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:55:13,691][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:55:14,194][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:55:14,696][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:55:15,199][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:55:15,701][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:55:16,203][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:55:16,705][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:55:17,207][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:55:17,708][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:55:18,210][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:55:18,712][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:55:19,217][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:55:19,719][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:55:20,221][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:55:20,723][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:55:21,224][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:55:21,726][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:55:22,228][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:55:22,730][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:55:23,234][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:55:23,737][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:55:24,238][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:55:24,739][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:55:25,241][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:55:25,743][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:55:26,244][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:55:26,744][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:55:27,245][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:55:27,746][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:55:28,248][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:55:28,750][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:55:29,252][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:55:29,754][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:55:30,256][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:55:30,757][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:55:31,259][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:55:31,762][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:55:32,263][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:55:32,766][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:55:33,268][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:55:33,770][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:55:34,273][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:55:34,776][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:55:35,278][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:55:35,780][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:55:36,282][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:55:36,783][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:55:37,284][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:55:37,785][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:55:38,286][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:55:38,788][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:55:39,289][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:55:39,790][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:55:40,295][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:55:40,799][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:55:41,305][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:55:41,810][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:55:42,317][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:55:42,822][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:55:43,326][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:55:43,831][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:55:44,335][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:55:44,837][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:55:45,339][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:55:45,841][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:55:46,343][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:55:46,844][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:55:47,345][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:55:47,847][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:55:48,349][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:55:48,852][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:55:49,353][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:55:49,855][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:55:50,357][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:55:50,859][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:55:51,361][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:55:51,863][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:55:52,365][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:55:52,868][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:55:53,370][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:55:53,873][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:55:54,375][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:55:54,878][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:55:55,382][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:55:55,884][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:55:56,385][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:55:56,885][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:55:57,386][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:55:57,886][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:55:58,387][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:55:58,889][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:55:59,389][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:55:59,890][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:56:00,392][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:56:00,895][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:56:01,396][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:56:01,897][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:56:02,399][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:56:02,901][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:56:03,402][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:56:03,904][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-26 01:56:04,514][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:04 [2026-03-26 01:56:05,254][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:56:05,257][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:56:05,258][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:56:05,925][__main__][INFO] - Iteration 477 took 1m 14s (8.89% Gen, 90.22% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 37m 57s. Estimated total time: 61h 58m 50s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 57s, 500 more iterations: 10h 19m 48s. [2026-03-26 01:56:05,927][__main__][INFO] - Starting iteration 477. [2026-03-26 01:56:06,328][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:56:06,328][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:56:06,924][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:56:09,337][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:56:13,136][__main__][INFO] - Number of regex retries in iteration 477: 2 [2026-03-26 01:56:13,137][__main__][INFO] - agents played in iteration 477 are Bob, Alice [2026-03-26 01:56:14,045][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:56:14,884][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:56:15,341][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:56:15,845][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:56:16,345][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:56:16,847][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:56:17,348][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:56:17,847][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:56:18,347][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:56:18,847][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:56:19,350][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:56:19,852][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:56:20,354][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:56:20,855][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:56:21,356][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:56:21,857][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:56:22,358][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:56:22,859][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:56:23,362][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:56:23,864][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:56:24,366][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:56:24,868][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:56:25,370][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:56:25,872][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:56:26,374][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:56:26,875][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:56:27,378][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:56:27,881][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:56:28,383][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:56:28,885][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:56:29,387][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:56:29,889][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:56:30,389][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:56:30,891][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:56:31,394][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:56:31,896][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:56:32,398][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:56:32,899][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:56:33,401][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:56:33,903][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:56:34,404][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:56:34,906][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:56:35,426][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:56:35,934][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:56:36,436][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:56:36,939][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:56:37,442][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:56:37,945][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:56:38,447][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:56:38,949][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:56:39,452][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:56:39,953][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:56:40,455][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:56:40,957][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:56:41,460][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:56:41,962][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:56:42,465][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:56:42,967][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:56:43,466][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:56:43,965][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:56:44,464][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:56:44,963][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:56:45,462][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:56:45,963][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:56:46,463][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:56:46,963][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:56:47,462][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:56:47,962][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:56:48,462][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:56:48,963][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:56:49,463][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:56:49,963][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:56:50,463][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:56:50,963][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:56:51,464][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:56:51,964][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:56:52,465][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:56:52,966][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:56:53,467][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:56:53,967][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:56:54,467][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:56:54,968][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:56:55,470][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:56:55,972][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:56:56,474][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:56:56,975][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:56:57,477][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:56:57,979][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:56:58,481][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:56:58,983][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:56:59,485][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:56:59,987][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:57:00,487][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:57:00,988][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:57:01,489][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:57:01,991][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:57:02,492][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:57:02,993][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:57:03,495][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:57:03,996][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:57:04,498][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:57:04,999][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:57:05,501][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:57:06,002][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:57:06,503][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:57:07,003][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:57:07,506][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:57:08,007][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:57:08,509][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:57:09,011][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:57:09,514][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:57:10,016][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:57:10,520][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:57:11,022][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:57:11,526][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:57:12,028][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:57:12,529][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:57:13,031][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:57:13,534][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:57:14,036][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:57:14,538][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:57:15,040][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:57:15,541][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:57:16,041][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:57:16,543][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:57:17,044][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:57:17,544][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:57:18,044][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:57:18,544][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:57:19,044][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-26 01:57:19,650][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.38%, ΔTime: 00:01:04 [2026-03-26 01:57:20,390][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:57:20,392][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:57:20,393][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:57:21,257][__main__][INFO] - Iteration 478 took 1m 14s (9.09% Gen, 89.76% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 52h 4m 23s. Estimated total time: 62h 26m 30s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 53s, 500 more iterations: 10h 24m 25s. [2026-03-26 01:57:21,260][__main__][INFO] - Starting iteration 478. [2026-03-26 01:57:21,659][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:57:21,660][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:57:23,442][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:57:29,124][__main__][INFO] - Number of regex retries in iteration 478: 1 [2026-03-26 01:57:29,125][__main__][INFO] - agents played in iteration 478 are Bob, Alice [2026-03-26 01:57:30,035][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:57:30,613][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:57:31,070][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:57:31,576][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:57:32,079][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:57:32,582][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:57:33,084][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:57:33,586][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:57:34,086][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:57:34,586][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:57:35,092][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:57:35,596][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:57:36,100][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:57:36,604][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:57:37,107][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:57:37,614][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:57:38,119][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:57:38,623][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:57:39,123][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:57:39,624][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:57:40,125][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:57:40,626][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:57:41,127][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:57:41,627][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:57:42,127][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:57:42,627][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:57:43,127][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:57:43,626][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:57:44,126][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:57:44,628][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:57:45,128][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:57:45,629][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:57:46,129][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:57:46,630][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:57:47,132][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:57:47,633][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:57:48,134][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:57:48,636][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:57:49,138][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:57:49,640][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:57:50,141][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:57:50,644][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:57:51,146][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:57:51,648][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:57:52,149][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:57:52,652][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:57:53,154][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:57:53,656][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:57:54,159][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:57:54,662][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:57:55,164][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:57:55,665][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:57:56,167][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:57:56,669][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:57:57,171][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:57:57,673][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:57:58,173][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:57:58,676][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:57:59,177][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:57:59,677][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:58:00,177][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:58:00,678][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:58:01,178][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:58:01,678][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:58:02,178][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:58:02,677][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:58:03,178][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:58:03,679][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:58:04,181][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:58:04,681][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:58:05,182][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:58:05,683][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:58:06,184][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:58:06,685][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:58:07,190][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:58:07,693][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:58:08,197][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:58:08,702][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:58:09,205][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:58:09,709][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:58:10,213][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:58:10,718][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:58:11,219][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:58:11,720][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:58:12,221][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:58:12,721][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:58:13,221][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:58:13,721][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:58:14,223][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:58:14,725][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:58:15,225][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:58:15,726][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:58:16,226][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:58:16,727][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:58:17,229][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:58:17,732][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:58:18,234][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:58:18,736][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:58:19,237][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:58:19,738][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:58:20,238][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:58:20,740][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:58:21,241][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:58:21,742][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:58:22,243][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:58:22,744][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:58:23,246][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:58:23,749][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:58:24,251][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:58:24,753][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:58:25,255][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:58:25,757][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:58:26,259][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:58:26,761][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:58:27,263][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:58:27,764][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:58:28,265][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:58:28,766][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:58:29,267][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:58:29,768][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:58:30,270][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:58:30,771][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:58:31,272][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:58:31,771][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:58:32,272][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:58:32,774][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:58:33,275][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:58:33,776][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:58:34,276][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:58:34,776][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-26 01:58:35,387][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:04 [2026-03-26 01:58:36,122][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:58:36,124][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:58:36,125][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:58:36,778][__main__][INFO] - Iteration 479 took 1m 15s (9.94% Gen, 89.19% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 52h 12m 33s. Estimated total time: 62h 35m 57s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 11s, 500 more iterations: 10h 25m 59s. [2026-03-26 01:58:36,780][__main__][INFO] - Starting iteration 479. [2026-03-26 01:58:37,178][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:58:37,179][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:58:37,773][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:58:43,787][__main__][INFO] - Number of regex retries in iteration 479: 1 [2026-03-26 01:58:43,788][__main__][INFO] - agents played in iteration 479 are Bob, Alice [2026-03-26 01:58:44,693][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:58:45,272][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 01:58:45,729][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 01:58:46,234][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 01:58:46,736][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 01:58:47,238][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 01:58:47,739][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 01:58:48,241][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 01:58:48,742][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 01:58:49,243][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 01:58:49,746][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 01:58:50,248][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 01:58:50,749][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 01:58:51,254][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 01:58:51,757][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 01:58:52,259][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 01:58:52,762][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 01:58:53,265][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 01:58:53,767][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 01:58:54,268][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 01:58:54,771][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 01:58:55,272][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 01:58:55,776][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 01:58:56,277][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 01:58:56,777][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 01:58:57,278][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 01:58:57,780][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 01:58:58,282][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 01:58:58,783][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 01:58:59,284][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 01:58:59,785][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 01:59:00,287][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 01:59:00,789][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 01:59:01,290][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 01:59:01,793][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 01:59:02,298][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 01:59:02,802][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 01:59:03,305][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 01:59:03,808][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 01:59:04,311][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 01:59:04,814][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 01:59:05,319][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 01:59:05,822][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 01:59:06,324][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 01:59:06,826][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 01:59:07,327][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 01:59:07,829][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 01:59:08,331][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 01:59:08,834][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 01:59:09,336][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 01:59:09,837][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 01:59:10,338][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 01:59:10,839][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 01:59:11,341][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 01:59:11,844][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 01:59:12,344][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 01:59:12,844][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 01:59:13,344][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 01:59:13,845][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 01:59:14,347][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 01:59:14,849][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 01:59:15,351][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 01:59:15,853][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 01:59:16,355][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 01:59:16,856][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 01:59:17,358][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 01:59:17,859][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 01:59:18,362][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 01:59:18,864][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 01:59:19,365][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 01:59:19,867][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 01:59:20,367][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 01:59:20,868][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 01:59:21,370][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 01:59:21,872][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 01:59:22,374][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 01:59:22,875][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 01:59:23,377][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 01:59:23,879][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 01:59:24,381][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 01:59:24,883][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 01:59:25,384][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 01:59:25,885][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 01:59:26,386][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 01:59:26,887][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 01:59:27,389][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 01:59:27,889][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 01:59:28,389][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 01:59:28,890][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 01:59:29,393][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 01:59:29,896][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 01:59:30,398][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 01:59:30,899][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 01:59:31,401][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 01:59:31,902][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 01:59:32,404][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 01:59:32,904][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 01:59:33,406][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 01:59:33,909][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 01:59:34,412][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 01:59:34,915][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 01:59:35,419][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 01:59:35,922][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 01:59:36,425][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 01:59:36,928][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 01:59:37,432][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 01:59:37,936][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 01:59:38,438][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 01:59:38,940][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 01:59:39,442][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 01:59:39,944][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 01:59:40,445][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 01:59:40,947][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 01:59:41,450][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 01:59:41,952][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 01:59:42,452][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 01:59:42,952][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 01:59:43,452][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 01:59:43,954][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 01:59:44,455][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 01:59:44,956][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 01:59:45,457][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 01:59:45,957][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 01:59:46,459][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 01:59:46,961][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 01:59:47,464][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 01:59:47,965][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 01:59:48,467][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 01:59:48,969][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 01:59:49,469][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 01:59:50,089][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:04 [2026-03-26 01:59:50,833][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 01:59:50,835][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 01:59:50,837][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 01:59:51,677][__main__][INFO] - Iteration 480 took 1m 14s (8.87% Gen, 90.00% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 40m 17s. Estimated total time: 62h 4m 56s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 9s, 500 more iterations: 10h 20m 49s. [2026-03-26 01:59:51,680][__main__][INFO] - Starting iteration 480. [2026-03-26 01:59:52,082][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 01:59:52,082][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 01:59:53,772][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 01:59:58,414][__main__][INFO] - Number of regex retries in iteration 480: 1 [2026-03-26 01:59:58,414][__main__][INFO] - agents played in iteration 480 are Bob, Alice [2026-03-26 01:59:59,319][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 01:59:59,896][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:00:00,358][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:00:00,868][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:00:01,372][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:00:01,878][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:00:02,382][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:00:02,887][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:00:03,390][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:00:03,895][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:00:04,397][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:00:04,898][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:00:05,399][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:00:05,901][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:00:06,402][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:00:06,903][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:00:07,404][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:00:07,905][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:00:08,407][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:00:08,908][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:00:09,409][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:00:09,911][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:00:10,414][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:00:10,916][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:00:11,421][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:00:11,923][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:00:12,425][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:00:12,926][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:00:13,428][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:00:13,930][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:00:14,432][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:00:14,934][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:00:15,437][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:00:15,939][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:00:16,442][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:00:16,945][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:00:17,447][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:00:17,949][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:00:18,451][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:00:18,955][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:00:19,458][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:00:19,962][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:00:20,464][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:00:20,965][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:00:21,466][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:00:21,969][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:00:22,470][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:00:22,972][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:00:23,473][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:00:23,974][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:00:24,476][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:00:24,979][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:00:25,483][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:00:25,985][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:00:26,489][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:00:26,991][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:00:27,496][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:00:27,999][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:00:28,498][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:00:28,996][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:00:29,494][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:00:29,992][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:00:30,489][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:00:30,986][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:00:31,484][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:00:31,981][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:00:32,485][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:00:32,990][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:00:33,494][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:00:33,999][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:00:34,504][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:00:35,008][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:00:35,513][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:00:36,019][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:00:36,521][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:00:37,022][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:00:37,524][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:00:38,025][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:00:38,527][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:00:39,028][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:00:39,529][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:00:40,032][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:00:40,535][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:00:41,038][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:00:41,543][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:00:42,045][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:00:42,547][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:00:43,049][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:00:43,550][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:00:44,053][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:00:44,554][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:00:45,056][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:00:45,558][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:00:46,060][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:00:46,562][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:00:47,064][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:00:47,565][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:00:48,067][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:00:48,570][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:00:49,073][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:00:49,576][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:00:50,078][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:00:50,580][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:00:51,083][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:00:51,585][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:00:52,088][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:00:52,589][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:00:53,090][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:00:53,592][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:00:54,095][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:00:54,596][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:00:55,098][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:00:55,600][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:00:56,102][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:00:56,604][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:00:57,106][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:00:57,610][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:00:58,113][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:00:58,616][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:00:59,119][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:00:59,623][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:01:00,125][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:01:00,624][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:01:01,122][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:01:01,620][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:01:02,119][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:01:02,618][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:01:03,115][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:01:03,615][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:01:04,115][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21759 tokens. [2026-03-26 02:01:04,746][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:04 [2026-03-26 02:01:05,494][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:01:05,497][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:01:05,498][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:01:06,242][__main__][INFO] - Iteration 481 took 1m 14s (8.54% Gen, 90.46% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 22m 9s. Estimated total time: 61h 48m 2s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 36s, 500 more iterations: 10h 18m 0s. [2026-03-26 02:01:06,244][__main__][INFO] - Starting iteration 481. [2026-03-26 02:01:06,642][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:01:06,642][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:01:12,824][mllm.models.large_language_model_local][WARNING] - Response Proposal: 11 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:01:13,841][__main__][INFO] - Number of regex retries in iteration 481: 1 [2026-03-26 02:01:13,842][__main__][INFO] - agents played in iteration 481 are Bob, Alice [2026-03-26 02:01:14,750][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:01:15,329][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:01:15,788][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:01:16,297][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:01:16,800][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:01:17,302][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:01:17,804][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:01:18,305][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:01:18,806][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:01:19,308][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:01:19,809][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:01:20,310][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:01:20,812][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:01:21,315][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:01:21,817][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:01:22,318][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:01:22,820][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:01:23,321][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:01:23,823][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:01:24,324][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:01:24,826][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:01:25,327][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:01:25,828][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:01:26,330][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:01:26,831][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:01:27,333][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:01:27,837][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:01:28,338][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:01:28,840][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:01:29,342][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:01:29,844][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:01:30,345][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:01:30,847][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:01:31,349][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:01:31,850][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:01:32,351][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:01:32,852][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:01:33,352][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:01:33,855][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:01:34,355][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:01:34,857][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:01:35,358][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:01:35,858][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:01:36,359][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:01:36,859][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:01:37,360][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:01:37,860][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:01:38,361][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:01:38,862][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:01:39,362][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:01:39,864][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:01:40,366][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:01:40,866][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:01:41,370][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:01:41,872][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:01:42,373][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:01:42,873][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:01:43,376][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:01:43,879][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:01:44,381][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:01:44,882][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:01:45,384][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:01:45,885][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:01:46,386][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:01:46,888][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:01:47,390][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:01:47,891][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:01:48,393][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:01:48,895][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:01:49,397][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:01:49,899][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:01:50,401][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:01:50,903][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:01:51,404][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:01:51,905][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:01:52,407][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:01:52,909][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:01:53,411][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:01:53,912][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:01:54,414][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:01:54,916][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:01:55,418][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:01:55,920][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:01:56,421][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:01:56,922][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:01:57,424][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:01:57,925][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:01:58,427][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:01:58,928][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:01:59,431][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:01:59,932][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:02:00,434][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:02:00,935][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:02:01,438][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:02:01,939][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:02:02,442][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:02:02,943][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:02:03,444][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:02:03,945][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:02:04,447][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:02:04,948][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:02:05,449][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:02:05,950][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:02:06,450][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:02:06,950][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:02:07,451][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:02:07,952][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:02:08,453][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:02:08,954][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:02:09,455][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:02:09,955][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:02:10,456][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:02:10,957][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:02:11,460][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:02:11,962][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:02:12,464][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:02:12,964][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:02:13,466][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:02:13,966][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:02:14,467][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:02:14,969][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:02:15,471][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:02:15,973][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:02:16,475][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:02:16,976][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:02:17,478][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:02:17,980][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:02:18,482][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:02:18,983][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:02:19,485][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-26 02:02:20,094][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-26 02:02:20,829][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:02:20,831][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:02:20,833][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:02:21,485][__main__][INFO] - Iteration 482 took 1m 14s (9.62% Gen, 89.51% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 51h 55m 2s. Estimated total time: 62h 22m 10s. Time estimates for 10 more iterations: 12m 28s, 100 more iterations: 2h 4m 44s, 500 more iterations: 10h 23m 41s. [2026-03-26 02:02:21,487][__main__][INFO] - Starting iteration 482. [2026-03-26 02:02:21,884][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:02:21,885][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:02:22,470][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:02:28,992][__main__][INFO] - Number of regex retries in iteration 482: 1 [2026-03-26 02:02:28,993][__main__][INFO] - agents played in iteration 482 are Bob, Alice [2026-03-26 02:02:29,898][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:02:30,474][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:02:30,932][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:02:31,439][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:02:31,942][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:02:32,444][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:02:32,945][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:02:33,446][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:02:33,947][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:02:34,448][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:02:34,948][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:02:35,449][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:02:35,949][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:02:36,451][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:02:36,954][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:02:37,457][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:02:37,959][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:02:38,460][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:02:38,962][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:02:39,463][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:02:39,965][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:02:40,466][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:02:40,967][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:02:41,470][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:02:41,971][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:02:42,473][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:02:42,975][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:02:43,475][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:02:43,977][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:02:44,478][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:02:44,980][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:02:45,481][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:02:45,982][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:02:46,483][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:02:46,984][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:02:47,485][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:02:47,986][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:02:48,486][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:02:48,988][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:02:49,489][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:02:49,989][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:02:50,489][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:02:50,989][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:02:51,490][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:02:51,989][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:02:52,490][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:02:52,989][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:02:53,490][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:02:53,989][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:02:54,490][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:02:55,000][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:02:55,501][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:02:56,003][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:02:56,505][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:02:57,007][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:02:57,510][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:02:58,014][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:02:58,516][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:02:59,017][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:02:59,519][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:03:00,020][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:03:00,522][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:03:01,024][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:03:01,525][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:03:02,025][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:03:02,526][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:03:03,029][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:03:03,531][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:03:04,034][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:03:04,536][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:03:05,039][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:03:05,541][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:03:06,043][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:03:06,544][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:03:07,045][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:03:07,547][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:03:08,047][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:03:08,548][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:03:09,049][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:03:09,550][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:03:10,051][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:03:10,552][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:03:11,053][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:03:11,556][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:03:12,057][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:03:12,558][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:03:13,059][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:03:13,561][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:03:14,062][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:03:14,563][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:03:15,064][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:03:15,565][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:03:16,066][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:03:16,567][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:03:17,068][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:03:17,569][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:03:18,070][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:03:18,570][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:03:19,072][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:03:19,573][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:03:20,075][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:03:20,575][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:03:21,077][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:03:21,579][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:03:22,081][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:03:22,583][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:03:23,086][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:03:23,589][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:03:24,091][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:03:24,594][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:03:25,096][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:03:25,598][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:03:26,099][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:03:26,600][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:03:27,102][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:03:27,604][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:03:28,106][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:03:28,609][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:03:29,112][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:03:29,614][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:03:30,116][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:03:30,620][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:03:31,123][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:03:31,624][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:03:32,126][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:03:32,628][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:03:33,130][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:03:33,633][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:03:34,135][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:03:34,636][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 02:03:35,250][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-26 02:03:35,986][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:03:35,989][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:03:35,990][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:03:36,644][__main__][INFO] - Iteration 483 took 1m 14s (9.51% Gen, 89.62% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 51h 49m 37s. Estimated total time: 62h 18m 0s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 36s, 500 more iterations: 10h 23m 0s. [2026-03-26 02:03:36,646][__main__][INFO] - Starting iteration 483. [2026-03-26 02:03:37,047][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:03:37,047][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:03:40,940][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:03:44,581][__main__][INFO] - Number of regex retries in iteration 483: 1 [2026-03-26 02:03:44,582][__main__][INFO] - agents played in iteration 483 are Bob, Alice [2026-03-26 02:03:45,492][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:03:46,335][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:03:46,793][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:03:47,299][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:03:47,801][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:03:48,303][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:03:48,804][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:03:49,306][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:03:49,808][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:03:50,310][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:03:50,811][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:03:51,313][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:03:51,816][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:03:52,318][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:03:52,820][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:03:53,321][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:03:53,822][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:03:54,323][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:03:54,823][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:03:55,323][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:03:55,824][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:03:56,326][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:03:56,827][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:03:57,327][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:03:57,827][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:03:58,326][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:03:58,827][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:03:59,327][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:03:59,828][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:04:00,328][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:04:00,828][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:04:01,330][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:04:01,829][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:04:02,330][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:04:02,831][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:04:03,331][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:04:03,832][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:04:04,333][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:04:04,836][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:04:05,336][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:04:05,837][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:04:06,338][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:04:06,838][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:04:07,343][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:04:07,843][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:04:08,343][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:04:08,844][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:04:09,344][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:04:09,844][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:04:10,345][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:04:10,847][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:04:11,352][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:04:11,855][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:04:12,357][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:04:12,858][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:04:13,360][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:04:13,861][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:04:14,362][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:04:14,863][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:04:15,364][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:04:15,865][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:04:16,365][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:04:16,866][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:04:17,366][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:04:17,866][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:04:18,366][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:04:18,867][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:04:19,368][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:04:19,870][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:04:20,370][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:04:20,872][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:04:21,374][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:04:21,875][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:04:22,376][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:04:22,877][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:04:23,378][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:04:23,878][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:04:24,379][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:04:24,882][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:04:25,384][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:04:25,885][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:04:26,386][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:04:26,885][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:04:27,386][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:04:27,886][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:04:28,386][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:04:28,886][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:04:29,387][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:04:29,888][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:04:30,388][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:04:30,890][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:04:31,390][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:04:31,890][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:04:32,391][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:04:32,891][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:04:33,390][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:04:33,892][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:04:34,394][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:04:34,894][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:04:35,395][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:04:35,896][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:04:36,396][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:04:36,896][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:04:37,397][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:04:37,897][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:04:38,397][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:04:38,897][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:04:39,397][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:04:39,897][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:04:40,398][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:04:40,897][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:04:41,399][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:04:41,900][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:04:42,400][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:04:42,901][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:04:43,402][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:04:43,902][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:04:44,404][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:04:44,906][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:04:45,406][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:04:45,908][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:04:46,409][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:04:46,908][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:04:47,408][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:04:47,908][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:04:48,409][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:04:48,908][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:04:49,409][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:04:49,908][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:04:50,408][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21724 tokens. [2026-03-26 02:04:51,021][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.16%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.23%, ΔTime: 00:01:04 [2026-03-26 02:04:51,756][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:04:51,758][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:04:51,759][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:04:52,408][__main__][INFO] - Iteration 484 took 1m 15s (10.00% Gen, 89.14% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 18m 26s. Estimated total time: 62h 48m 5s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 36s, 500 more iterations: 10h 28m 0s. [2026-03-26 02:04:52,410][__main__][INFO] - Starting iteration 484. [2026-03-26 02:04:52,810][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:04:52,810][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:04:59,994][__main__][INFO] - Number of regex retries in iteration 484: 0 [2026-03-26 02:04:59,995][__main__][INFO] - agents played in iteration 484 are Bob, Alice [2026-03-26 02:05:00,908][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:05:01,487][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:05:01,945][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:05:02,453][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:05:02,956][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:05:03,459][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:05:03,962][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:05:04,463][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:05:04,966][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:05:05,468][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:05:05,970][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:05:06,473][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:05:06,975][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:05:07,477][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:05:07,978][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:05:08,480][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:05:08,982][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:05:09,484][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:05:09,985][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:05:10,486][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:05:10,987][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:05:11,491][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:05:11,994][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:05:12,496][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:05:12,998][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:05:13,499][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:05:14,004][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:05:14,508][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:05:15,011][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:05:15,513][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:05:16,017][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:05:16,521][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:05:17,025][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:05:17,528][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:05:18,032][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:05:18,536][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:05:19,040][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:05:19,544][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:05:20,048][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:05:20,551][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:05:21,053][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:05:21,556][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:05:22,058][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:05:22,561][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:05:23,063][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:05:23,565][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:05:24,066][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:05:24,568][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:05:25,071][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:05:25,576][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:05:26,078][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:05:26,579][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:05:27,080][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:05:27,581][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:05:28,081][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:05:28,583][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:05:29,083][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:05:29,585][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:05:30,085][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:05:30,586][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:05:31,086][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:05:31,588][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:05:32,089][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:05:32,589][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:05:33,091][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:05:33,592][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:05:34,094][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:05:34,596][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:05:35,098][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:05:35,600][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:05:36,102][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:05:36,602][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:05:37,106][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:05:37,610][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:05:38,112][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:05:38,614][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:05:39,117][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:05:39,620][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:05:40,123][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:05:40,625][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:05:41,127][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:05:41,630][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:05:42,133][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:05:42,635][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:05:43,137][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:05:43,640][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:05:44,142][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:05:44,644][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:05:45,145][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:05:45,647][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:05:46,150][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:05:46,654][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:05:47,157][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:05:47,661][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:05:48,164][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:05:48,667][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:05:49,170][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:05:49,673][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:05:50,177][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:05:50,679][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:05:51,182][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:05:51,684][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:05:52,186][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:05:52,689][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:05:53,191][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:05:53,695][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:05:54,198][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:05:54,699][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:05:55,201][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:05:55,702][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:05:56,203][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:05:56,704][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:05:57,205][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:05:57,707][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:05:58,207][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:05:58,708][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:05:59,208][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:05:59,711][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:06:00,212][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:06:00,713][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:06:01,215][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:06:01,717][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:06:02,219][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:06:02,721][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:06:03,223][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:06:03,725][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:06:04,227][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:06:04,727][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:06:05,229][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:06:05,731][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 02:06:06,343][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 02:06:07,099][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:06:07,101][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:06:07,103][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:06:07,780][__main__][INFO] - Iteration 485 took 1m 14s (9.58% Gen, 89.51% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 57m 37s. Estimated total time: 62h 28m 32s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 57s, 500 more iterations: 10h 24m 45s. [2026-03-26 02:06:07,782][__main__][INFO] - Starting iteration 485. [2026-03-26 02:06:08,182][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:06:08,182][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:06:14,340][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 20 balls / 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:06:16,210][__main__][INFO] - Number of regex retries in iteration 485: 1 [2026-03-26 02:06:16,211][__main__][INFO] - agents played in iteration 485 are Bob, Alice [2026-03-26 02:06:17,118][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:06:17,694][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:06:18,151][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:06:18,657][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:06:19,160][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:06:19,661][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:06:20,163][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:06:20,665][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:06:21,166][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:06:21,666][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:06:22,170][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:06:22,672][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:06:23,174][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:06:23,675][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:06:24,176][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:06:24,677][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:06:25,179][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:06:25,681][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:06:26,186][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:06:26,689][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:06:27,191][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:06:27,696][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:06:28,198][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:06:28,701][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:06:29,204][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:06:29,705][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:06:30,206][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:06:30,707][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:06:31,209][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:06:31,711][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:06:32,213][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:06:32,714][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:06:33,216][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:06:33,717][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:06:34,218][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:06:34,719][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:06:35,219][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:06:35,720][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:06:36,222][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:06:36,723][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:06:37,223][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:06:37,723][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:06:38,223][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:06:38,723][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:06:39,223][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:06:39,723][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:06:40,223][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:06:40,723][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:06:41,226][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:06:41,727][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:06:42,230][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:06:42,732][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:06:43,236][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:06:43,739][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:06:44,242][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:06:44,744][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:06:45,246][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:06:45,747][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:06:46,249][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:06:46,750][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:06:47,253][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:06:47,755][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:06:48,257][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:06:48,758][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:06:49,261][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:06:49,762][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:06:50,263][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:06:50,763][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:06:51,264][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:06:51,764][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:06:52,264][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:06:52,765][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:06:53,265][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:06:53,765][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:06:54,267][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:06:54,768][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:06:55,270][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:06:55,771][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:06:56,273][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:06:56,775][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:06:57,277][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:06:57,779][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:06:58,281][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:06:58,783][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:06:59,284][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:06:59,786][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:07:00,288][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:07:00,789][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:07:01,291][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:07:01,793][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:07:02,297][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:07:02,798][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:07:03,299][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:07:03,801][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:07:04,302][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:07:04,802][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:07:05,303][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:07:05,804][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:07:06,306][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:07:06,808][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:07:07,312][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:07:07,815][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:07:08,317][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:07:08,818][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:07:09,320][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:07:09,822][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:07:10,322][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:07:10,822][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:07:11,324][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:07:11,825][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:07:12,326][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:07:12,826][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:07:13,326][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:07:13,826][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:07:14,327][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:07:14,829][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:07:15,331][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:07:15,833][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:07:16,336][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:07:16,839][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:07:17,341][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:07:17,843][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:07:18,346][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:07:18,848][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:07:19,350][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:07:19,851][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:07:20,355][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:07:20,858][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:07:21,360][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:07:21,862][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21743 tokens. [2026-03-26 02:07:22,479][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-26 02:07:23,220][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:07:23,222][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:07:23,224][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:07:23,888][__main__][INFO] - Iteration 486 took 1m 15s (10.61% Gen, 88.52% Train). Generation: 8s, Training: 1m 7s. Estimated remaining time: 52h 33m 11s. Estimated total time: 63h 5m 21s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 10s, 500 more iterations: 10h 30m 53s. [2026-03-26 02:07:23,890][__main__][INFO] - Starting iteration 486. [2026-03-26 02:07:24,290][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:07:24,291][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:07:32,090][__main__][INFO] - Number of regex retries in iteration 486: 0 [2026-03-26 02:07:32,091][__main__][INFO] - agents played in iteration 486 are Bob, Alice [2026-03-26 02:07:32,997][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:07:33,572][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:07:34,032][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:07:34,539][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:07:35,042][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:07:35,544][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:07:36,046][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:07:36,549][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:07:37,052][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:07:37,554][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:07:38,055][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:07:38,557][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:07:39,059][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:07:39,561][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:07:40,062][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:07:40,563][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:07:41,065][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:07:41,568][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:07:42,071][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:07:42,573][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:07:43,075][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:07:43,577][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:07:44,079][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:07:44,582][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:07:45,084][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:07:45,586][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:07:46,091][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:07:46,594][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:07:47,097][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:07:47,602][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:07:48,105][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:07:48,607][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:07:49,110][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:07:49,616][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:07:50,119][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:07:50,621][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:07:51,123][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:07:51,624][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:07:52,126][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:07:52,628][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:07:53,130][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:07:53,633][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:07:54,135][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:07:54,638][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:07:55,140][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:07:55,642][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:07:56,145][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:07:56,646][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:07:57,148][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:07:57,649][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:07:58,152][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:07:58,654][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:07:59,156][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:07:59,658][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:08:00,160][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:08:00,661][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:08:01,163][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:08:01,664][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:08:02,167][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:08:02,669][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:08:03,171][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:08:03,673][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:08:04,175][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:08:04,678][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:08:05,180][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:08:05,683][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:08:06,184][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:08:06,686][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:08:07,187][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:08:07,689][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:08:08,190][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:08:08,691][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:08:09,192][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:08:09,695][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:08:10,197][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:08:10,697][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:08:11,199][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:08:11,702][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:08:12,203][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:08:12,702][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:08:13,204][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:08:13,704][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:08:14,207][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:08:14,709][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:08:15,212][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:08:15,714][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:08:16,217][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:08:16,719][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:08:17,221][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:08:17,723][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:08:18,226][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:08:18,729][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:08:19,234][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:08:19,738][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:08:20,241][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:08:20,744][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:08:21,247][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:08:21,750][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:08:22,253][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:08:22,756][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:08:23,257][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:08:23,760][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:08:24,262][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:08:24,763][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:08:25,265][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:08:25,766][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:08:26,268][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:08:26,768][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:08:27,269][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:08:27,771][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:08:28,273][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:08:28,775][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:08:29,279][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:08:29,782][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:08:30,286][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:08:30,787][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:08:31,289][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:08:31,789][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:08:32,291][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:08:32,792][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:08:33,294][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:08:33,796][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:08:34,298][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:08:34,800][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:08:35,302][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:08:35,804][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:08:36,306][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:08:36,808][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:08:37,313][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:08:37,816][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21746 tokens. [2026-03-26 02:08:38,423][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-26 02:08:39,155][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:08:39,157][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:08:39,159][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:08:39,806][__main__][INFO] - Iteration 487 took 1m 15s (10.33% Gen, 88.81% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 22m 24s. Estimated total time: 62h 55m 50s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 51s, 500 more iterations: 10h 29m 18s. [2026-03-26 02:08:39,808][__main__][INFO] - Starting iteration 487. [2026-03-26 02:08:40,208][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:08:40,208][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:08:44,888][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:08:47,319][__main__][INFO] - Number of regex retries in iteration 487: 1 [2026-03-26 02:08:47,320][__main__][INFO] - agents played in iteration 487 are Bob, Alice [2026-03-26 02:08:48,227][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:08:48,805][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:08:49,262][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:08:49,768][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:08:50,269][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:08:50,770][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:08:51,271][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:08:51,775][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:08:52,276][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:08:52,777][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:08:53,279][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:08:53,779][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:08:54,280][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:08:54,781][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:08:55,281][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:08:55,783][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:08:56,284][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:08:56,784][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:08:57,287][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:08:57,789][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:08:58,291][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:08:58,793][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:08:59,295][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:08:59,796][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:09:00,297][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:09:00,799][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:09:01,300][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:09:01,801][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:09:02,302][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:09:02,803][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:09:03,303][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:09:03,803][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:09:04,303][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:09:04,804][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:09:05,307][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:09:05,809][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:09:06,310][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:09:06,812][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:09:07,316][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:09:07,817][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:09:08,318][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:09:08,820][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:09:09,321][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:09:09,822][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:09:10,323][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:09:10,824][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:09:11,328][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:09:11,830][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:09:12,331][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:09:12,833][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:09:13,336][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:09:13,836][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:09:14,337][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:09:14,838][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:09:15,336][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:09:15,838][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:09:16,337][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:09:16,839][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:09:17,339][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:09:17,840][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:09:18,341][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:09:18,842][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:09:19,342][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:09:19,844][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:09:20,344][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:09:20,845][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:09:21,346][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:09:21,846][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:09:22,345][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:09:22,845][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:09:23,345][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:09:23,845][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:09:24,345][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:09:24,846][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:09:25,347][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:09:25,848][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:09:26,349][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:09:26,850][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:09:27,351][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:09:27,852][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:09:28,353][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:09:28,854][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:09:29,356][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:09:29,859][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:09:30,363][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:09:30,867][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:09:31,368][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:09:31,869][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:09:32,369][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:09:32,870][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:09:33,371][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:09:33,873][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:09:34,374][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:09:34,875][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:09:35,375][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:09:35,876][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:09:36,377][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:09:36,878][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:09:37,380][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:09:37,881][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:09:38,382][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:09:38,884][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:09:39,385][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:09:39,886][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:09:40,387][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:09:40,890][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:09:41,392][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:09:41,894][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:09:42,395][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:09:42,896][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:09:43,397][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:09:43,898][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:09:44,399][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:09:44,900][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:09:45,400][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:09:45,900][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:09:46,400][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:09:46,900][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:09:47,401][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:09:47,900][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:09:48,401][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:09:48,901][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:09:49,401][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:09:49,900][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:09:50,401][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:09:50,901][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:09:51,401][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:09:51,901][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:09:52,402][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:09:52,902][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21737 tokens. [2026-03-26 02:09:53,516][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-26 02:09:54,248][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:09:54,250][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:09:54,252][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:09:55,077][__main__][INFO] - Iteration 488 took 1m 14s (9.50% Gen, 89.40% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 51h 48m 48s. Estimated total time: 62h 23m 30s. Time estimates for 10 more iterations: 12m 28s, 100 more iterations: 2h 4m 47s, 500 more iterations: 10h 23m 55s. [2026-03-26 02:09:55,080][__main__][INFO] - Starting iteration 488. [2026-03-26 02:09:55,481][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:09:55,482][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:09:56,071][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:10:02,131][__main__][INFO] - Number of regex retries in iteration 488: 1 [2026-03-26 02:10:02,132][__main__][INFO] - agents played in iteration 488 are Bob, Alice [2026-03-26 02:10:03,035][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:10:03,625][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:10:04,083][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:10:04,589][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:10:05,092][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:10:05,593][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:10:06,094][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:10:06,596][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:10:07,100][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:10:07,604][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:10:08,106][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:10:08,607][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:10:09,107][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:10:09,608][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:10:10,110][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:10:10,611][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:10:11,112][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:10:11,615][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:10:12,120][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:10:12,623][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:10:13,125][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:10:13,627][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:10:14,128][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:10:14,630][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:10:15,133][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:10:15,638][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:10:16,140][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:10:16,642][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:10:17,144][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:10:17,645][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:10:18,147][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:10:18,651][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:10:19,154][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:10:19,656][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:10:20,157][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:10:20,659][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:10:21,160][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:10:21,661][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:10:22,162][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:10:22,663][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:10:23,163][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:10:23,663][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:10:24,165][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:10:24,666][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:10:25,169][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:10:25,671][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:10:26,173][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:10:26,675][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:10:27,177][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:10:27,679][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:10:28,182][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:10:28,682][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:10:29,183][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:10:29,684][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:10:30,184][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:10:30,687][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:10:31,190][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:10:31,692][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:10:32,193][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:10:32,694][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:10:33,194][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:10:33,696][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:10:34,196][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:10:34,697][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:10:35,197][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:10:35,698][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:10:36,198][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:10:36,698][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:10:37,198][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:10:37,698][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:10:38,198][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:10:38,698][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:10:39,198][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:10:39,698][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:10:40,199][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:10:40,700][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:10:41,202][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:10:41,703][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:10:42,203][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:10:42,703][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:10:43,202][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:10:43,702][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:10:44,203][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:10:44,704][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:10:45,205][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:10:45,706][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:10:46,207][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:10:46,710][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:10:47,212][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:10:47,715][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:10:48,216][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:10:48,718][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:10:49,220][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:10:49,721][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:10:50,223][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:10:50,725][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:10:51,226][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:10:51,728][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:10:52,228][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:10:52,729][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:10:53,229][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:10:53,730][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:10:54,230][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:10:54,730][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:10:55,230][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:10:55,731][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:10:56,234][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:10:56,736][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:10:57,238][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:10:57,740][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:10:58,241][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:10:58,744][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:10:59,246][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:10:59,747][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:11:00,249][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:11:00,751][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:11:01,252][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:11:01,752][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:11:02,255][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:11:02,757][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:11:03,258][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:11:03,760][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:11:04,262][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:11:04,762][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:11:05,264][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:11:05,764][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:11:06,266][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:11:06,766][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:11:07,266][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:11:07,767][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21725 tokens. [2026-03-26 02:11:08,387][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-26 02:11:09,130][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:11:09,132][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:11:09,134][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:11:09,792][__main__][INFO] - Iteration 489 took 1m 14s (8.95% Gen, 90.16% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 19m 38s. Estimated total time: 61h 55m 34s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 51s, 500 more iterations: 10h 19m 15s. [2026-03-26 02:11:09,795][__main__][INFO] - Starting iteration 489. [2026-03-26 02:11:10,192][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:11:10,193][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:11:10,781][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:11:10,787][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:11:13,252][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:11:17,408][__main__][INFO] - Number of regex retries in iteration 489: 3 [2026-03-26 02:11:17,409][__main__][INFO] - agents played in iteration 489 are Bob, Alice [2026-03-26 02:11:18,318][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:11:18,907][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:11:19,365][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:11:19,872][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:11:20,374][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:11:20,877][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:11:21,379][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:11:21,881][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:11:22,383][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:11:22,885][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:11:23,386][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:11:23,887][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:11:24,389][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:11:24,890][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:11:25,392][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:11:25,894][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:11:26,398][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:11:26,901][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:11:27,404][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:11:27,906][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:11:28,409][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:11:28,911][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:11:29,416][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:11:29,919][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:11:30,421][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:11:30,924][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:11:31,425][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:11:31,928][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:11:32,431][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:11:32,934][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:11:33,436][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:11:33,938][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:11:34,440][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:11:34,942][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:11:35,446][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:11:35,950][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:11:36,453][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:11:36,956][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:11:37,463][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:11:37,965][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:11:38,468][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:11:38,970][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:11:39,475][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:11:39,979][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:11:40,481][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:11:40,985][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:11:41,489][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:11:41,991][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:11:42,493][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:11:42,997][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:11:43,500][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:11:44,001][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:11:44,503][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:11:45,005][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:11:45,507][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:11:46,009][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:11:46,512][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:11:47,015][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:11:47,518][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:11:48,021][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:11:48,524][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:11:49,026][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:11:49,530][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:11:50,032][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:11:50,536][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:11:51,041][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:11:51,543][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:11:52,046][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:11:52,548][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:11:53,050][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:11:53,552][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:11:54,055][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:11:54,558][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:11:55,061][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:11:55,563][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:11:56,064][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:11:56,565][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:11:57,067][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:11:57,569][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:11:58,070][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:11:58,571][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:11:59,073][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:11:59,574][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:12:00,077][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:12:00,579][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:12:01,081][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:12:01,584][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:12:02,086][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:12:02,588][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:12:03,090][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:12:03,592][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:12:04,093][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:12:04,594][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:12:05,095][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:12:05,597][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:12:06,097][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:12:06,598][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:12:07,098][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:12:07,600][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:12:08,102][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:12:08,603][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:12:09,105][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:12:09,607][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:12:10,109][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:12:10,611][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:12:11,113][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:12:11,618][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:12:12,123][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:12:12,626][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:12:13,128][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:12:13,632][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:12:14,135][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:12:14,639][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:12:15,143][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:12:15,646][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:12:16,148][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:12:16,649][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:12:17,152][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:12:17,655][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:12:18,157][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:12:18,660][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:12:19,162][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:12:19,667][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:12:20,170][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:12:20,674][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:12:21,177][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:12:21,680][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:12:22,182][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:12:22,685][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:12:23,187][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 02:12:23,828][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-26 02:12:24,569][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:12:24,571][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:12:24,572][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:12:25,255][__main__][INFO] - Iteration 490 took 1m 15s (9.61% Gen, 89.48% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 55m 57s. Estimated total time: 62h 33m 9s. Time estimates for 10 more iterations: 12m 30s, 100 more iterations: 2h 5m 6s, 500 more iterations: 10h 25m 31s. [2026-03-26 02:12:25,257][__main__][INFO] - Starting iteration 490. [2026-03-26 02:12:25,658][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:12:25,659][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:12:29,886][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:12:32,658][__main__][INFO] - Number of regex retries in iteration 490: 1 [2026-03-26 02:12:32,659][__main__][INFO] - agents played in iteration 490 are Bob, Alice [2026-03-26 02:12:33,836][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:12:34,418][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:12:34,876][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:12:35,384][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:12:35,885][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:12:36,387][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:12:36,888][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:12:37,390][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:12:37,893][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:12:38,394][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:12:38,898][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:12:39,401][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:12:39,903][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:12:40,404][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:12:40,907][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:12:41,411][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:12:41,915][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:12:42,418][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:12:42,920][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:12:43,420][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:12:43,921][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:12:44,422][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:12:44,922][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:12:45,422][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:12:45,923][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:12:46,423][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:12:46,923][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:12:47,422][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:12:47,921][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:12:48,420][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:12:48,921][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:12:49,420][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:12:49,919][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:12:50,419][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:12:50,920][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:12:51,421][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:12:51,922][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:12:52,423][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:12:52,923][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:12:53,424][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:12:53,925][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:12:54,426][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:12:54,927][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:12:55,430][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:12:55,932][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:12:56,434][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:12:56,936][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:12:57,438][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:12:57,940][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:12:58,442][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:12:58,943][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:12:59,444][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:12:59,944][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:13:00,446][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:13:00,947][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:13:01,447][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:13:01,948][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:13:02,449][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:13:02,949][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:13:03,450][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:13:03,951][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:13:04,451][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:13:04,952][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:13:05,454][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:13:05,955][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:13:06,456][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:13:06,959][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:13:07,463][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:13:07,964][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:13:08,465][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:13:08,966][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:13:09,467][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:13:09,968][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:13:10,469][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:13:10,970][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:13:11,476][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:13:11,978][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:13:12,481][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:13:12,984][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:13:13,485][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:13:13,987][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:13:14,488][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:13:14,989][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:13:15,490][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:13:15,990][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:13:16,491][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:13:16,992][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:13:17,494][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:13:17,995][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:13:18,499][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:13:18,998][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:13:19,498][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:13:19,998][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:13:20,497][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:13:20,996][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:13:21,495][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:13:21,995][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:13:22,495][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:13:22,997][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:13:23,498][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:13:23,999][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:13:24,500][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:13:25,001][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:13:25,502][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:13:26,003][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:13:26,504][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:13:27,004][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:13:27,506][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:13:28,007][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:13:28,509][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:13:29,011][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:13:29,513][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:13:30,015][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:13:30,518][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:13:31,018][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:13:31,519][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:13:32,020][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:13:32,521][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:13:33,022][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:13:33,524][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:13:34,025][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:13:34,528][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:13:35,028][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:13:35,529][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:13:36,029][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:13:36,537][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:13:37,039][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:13:37,543][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:13:38,052][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:13:38,568][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21735 tokens. [2026-03-26 02:13:39,217][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-26 02:13:39,953][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:13:39,955][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:13:39,957][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:13:40,674][__main__][INFO] - Iteration 491 took 1m 15s (9.33% Gen, 89.71% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 52m 22s. Estimated total time: 62h 30m 49s. Time estimates for 10 more iterations: 12m 30s, 100 more iterations: 2h 5m 1s, 500 more iterations: 10h 25m 8s. [2026-03-26 02:13:40,676][__main__][INFO] - Starting iteration 491. [2026-03-26 02:13:41,077][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:13:41,077][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:13:47,051][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:13:47,823][__main__][INFO] - Number of regex retries in iteration 491: 1 [2026-03-26 02:13:47,824][__main__][INFO] - agents played in iteration 491 are Bob, Alice [2026-03-26 02:13:49,028][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:13:49,609][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:13:50,066][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:13:50,570][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:13:51,070][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:13:51,569][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:13:52,070][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:13:52,570][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:13:53,070][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:13:53,571][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:13:54,068][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:13:54,565][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:13:55,062][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:13:55,559][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:13:56,057][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:13:56,555][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:13:57,053][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:13:57,551][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:13:58,054][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:13:58,557][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:13:59,059][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:13:59,561][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:14:00,064][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:14:00,567][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:14:01,069][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:14:01,571][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:14:02,071][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:14:02,574][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:14:03,075][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:14:03,577][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:14:04,078][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:14:04,581][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:14:05,083][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:14:05,589][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:14:06,091][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:14:06,594][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:14:07,103][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:14:07,606][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:14:08,108][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:14:08,619][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:14:09,122][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:14:09,628][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:14:10,132][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:14:10,637][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:14:11,141][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:14:11,647][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:14:12,150][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:14:12,654][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:14:13,158][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:14:13,661][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:14:14,165][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:14:14,667][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:14:15,170][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:14:15,675][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:14:16,178][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:14:16,681][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:14:17,183][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:14:17,685][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:14:18,189][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:14:18,691][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:14:19,194][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:14:19,697][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:14:20,200][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:14:20,702][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:14:21,204][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:14:21,706][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:14:22,207][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:14:22,707][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:14:23,207][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:14:23,707][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:14:24,207][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:14:24,706][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:14:25,207][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:14:25,707][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:14:26,205][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:14:26,702][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:14:27,199][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:14:27,698][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:14:28,196][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:14:28,694][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:14:29,192][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:14:29,690][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:14:30,192][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:14:30,694][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:14:31,197][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:14:31,699][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:14:32,202][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:14:32,704][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:14:33,206][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:14:33,707][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:14:34,208][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:14:34,711][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:14:35,214][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:14:35,717][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:14:36,219][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:14:36,721][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:14:37,224][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:14:37,726][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:14:38,228][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:14:38,728][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:14:39,228][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:14:39,728][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:14:40,229][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:14:40,729][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:14:41,232][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:14:41,735][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:14:42,237][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:14:42,739][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:14:43,242][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:14:43,744][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:14:44,246][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:14:44,747][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:14:45,249][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:14:45,750][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:14:46,251][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:14:46,753][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:14:47,259][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:14:47,761][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:14:48,263][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:14:48,765][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:14:49,266][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:14:49,774][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:14:50,278][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:14:50,782][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:14:51,285][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:14:51,787][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:14:52,294][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:14:52,799][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:14:53,303][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:14:53,806][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-26 02:14:54,450][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.38%, ΔTime: 00:01:04 [2026-03-26 02:14:55,185][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:14:55,188][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:14:55,189][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:14:55,909][__main__][INFO] - Iteration 492 took 1m 14s (9.02% Gen, 90.02% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 41m 56s. Estimated total time: 62h 21m 39s. Time estimates for 10 more iterations: 12m 28s, 100 more iterations: 2h 4m 43s, 500 more iterations: 10h 23m 36s. [2026-03-26 02:14:55,911][__main__][INFO] - Starting iteration 492. [2026-03-26 02:14:56,310][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:14:56,311][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:15:03,293][__main__][INFO] - Number of regex retries in iteration 492: 0 [2026-03-26 02:15:03,293][__main__][INFO] - agents played in iteration 492 are Bob, Alice [2026-03-26 02:15:04,206][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:15:04,783][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:15:05,243][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:15:05,751][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:15:06,253][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:15:06,754][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:15:07,257][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:15:07,759][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:15:08,262][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:15:08,765][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:15:09,267][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:15:09,769][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:15:10,270][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:15:10,773][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:15:11,278][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:15:11,781][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:15:12,283][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:15:12,785][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:15:13,286][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:15:13,787][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:15:14,288][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:15:14,789][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:15:15,289][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:15:15,790][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:15:16,291][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:15:16,792][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:15:17,295][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:15:17,797][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:15:18,297][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:15:18,800][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:15:19,301][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:15:19,803][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:15:20,304][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:15:20,805][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:15:21,305][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:15:21,805][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:15:22,306][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:15:22,806][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:15:23,307][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:15:23,807][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:15:24,308][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:15:24,808][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:15:25,309][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:15:25,810][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:15:26,311][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:15:26,811][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:15:27,312][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:15:27,813][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:15:28,314][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:15:28,817][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:15:29,317][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:15:29,818][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:15:30,318][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:15:30,819][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:15:31,319][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:15:31,820][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:15:32,321][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:15:32,823][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:15:33,324][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:15:33,826][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:15:34,327][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:15:34,829][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:15:35,330][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:15:35,836][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:15:36,339][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:15:36,843][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:15:37,346][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:15:37,848][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:15:38,349][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:15:38,851][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:15:39,353][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:15:39,854][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:15:40,356][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:15:40,858][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:15:41,362][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:15:41,865][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:15:42,367][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:15:42,868][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:15:43,369][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:15:43,870][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:15:44,372][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:15:44,873][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:15:45,374][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:15:45,875][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:15:46,375][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:15:46,877][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:15:47,378][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:15:47,878][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:15:48,378][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:15:48,880][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:15:49,381][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:15:49,883][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:15:50,384][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:15:50,885][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:15:51,386][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:15:51,889][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:15:52,390][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:15:52,892][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:15:53,394][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:15:53,895][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:15:54,396][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:15:54,897][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:15:55,398][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:15:55,898][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:15:56,399][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:15:56,900][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:15:57,400][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:15:57,901][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:15:58,401][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:15:58,901][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:15:59,401][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:15:59,901][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:16:00,401][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:16:00,907][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:16:01,409][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:16:01,909][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:16:02,411][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:16:02,912][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:16:03,415][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:16:03,916][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:16:04,418][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:16:04,924][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:16:05,427][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:16:05,930][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:16:06,432][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:16:06,936][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:16:07,441][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:16:07,945][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:16:08,447][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:16:08,957][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21724 tokens. [2026-03-26 02:16:09,590][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-26 02:16:10,324][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:16:10,326][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:16:10,327][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:16:11,092][__main__][INFO] - Iteration 493 took 1m 14s (9.34% Gen, 89.64% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 38m 8s. Estimated total time: 62h 19m 6s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 38s, 500 more iterations: 10h 23m 11s. [2026-03-26 02:16:11,094][__main__][INFO] - Starting iteration 493. [2026-03-26 02:16:11,492][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:16:11,492][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:16:18,501][__main__][INFO] - Number of regex retries in iteration 493: 0 [2026-03-26 02:16:18,502][__main__][INFO] - agents played in iteration 493 are Bob, Alice [2026-03-26 02:16:19,408][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:16:19,986][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:16:20,445][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:16:20,951][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:16:21,454][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:16:21,956][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:16:22,458][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:16:22,959][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:16:23,460][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:16:23,962][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:16:24,464][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:16:24,965][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:16:25,466][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:16:25,967][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:16:26,468][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:16:26,968][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:16:27,469][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:16:27,970][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:16:28,471][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:16:28,972][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:16:29,472][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:16:29,977][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:16:30,477][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:16:30,978][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:16:31,478][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:16:31,979][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:16:32,482][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:16:32,985][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:16:33,486][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:16:33,987][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:16:34,490][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:16:34,992][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:16:35,493][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:16:35,995][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:16:36,496][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:16:36,997][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:16:37,500][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:16:38,001][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:16:38,501][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:16:39,003][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:16:39,503][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:16:40,004][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:16:40,504][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:16:41,006][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:16:41,509][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:16:42,010][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:16:42,511][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:16:43,015][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:16:43,516][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:16:44,018][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:16:44,519][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:16:45,020][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:16:45,522][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:16:46,023][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:16:46,524][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:16:47,025][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:16:47,526][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:16:48,028][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:16:48,530][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:16:49,031][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:16:49,533][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:16:50,035][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:16:50,537][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:16:51,039][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:16:51,540][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:16:52,042][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:16:52,543][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:16:53,044][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:16:53,545][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:16:54,046][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:16:54,547][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:16:55,049][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:16:55,551][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:16:56,052][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:16:56,554][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:16:57,054][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:16:57,554][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:16:58,056][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:16:58,557][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:16:59,058][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:16:59,559][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:17:00,061][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:17:00,562][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:17:01,062][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:17:01,563][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:17:02,063][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:17:02,564][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:17:03,064][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:17:03,564][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:17:04,064][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:17:04,566][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:17:05,067][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:17:05,568][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:17:06,070][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:17:06,571][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:17:07,073][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:17:07,574][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:17:08,077][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:17:08,577][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:17:09,078][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:17:09,577][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:17:10,078][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:17:10,578][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:17:11,078][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:17:11,581][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:17:12,081][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:17:12,582][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:17:13,083][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:17:13,584][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:17:14,085][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:17:14,586][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:17:15,087][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:17:15,587][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:17:16,088][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:17:16,589][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:17:17,089][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:17:17,590][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:17:18,091][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:17:18,593][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:17:19,093][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:17:19,599][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:17:20,100][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:17:20,603][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:17:21,105][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:17:21,608][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:17:22,109][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:17:22,611][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:17:23,113][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:17:23,621][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:17:24,126][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-26 02:17:24,758][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-26 02:17:25,490][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:17:25,492][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:17:25,494][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:17:26,183][__main__][INFO] - Iteration 494 took 1m 14s (9.38% Gen, 89.69% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 51h 32m 23s. Estimated total time: 62h 14m 36s. Time estimates for 10 more iterations: 12m 26s, 100 more iterations: 2h 4m 29s, 500 more iterations: 10h 22m 26s. [2026-03-26 02:17:26,185][__main__][INFO] - Starting iteration 494. [2026-03-26 02:17:26,584][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:17:26,585][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:17:33,119][__main__][INFO] - Number of regex retries in iteration 494: 0 [2026-03-26 02:17:33,120][__main__][INFO] - agents played in iteration 494 are Bob, Alice [2026-03-26 02:17:34,030][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:17:34,604][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:17:35,063][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:17:35,570][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:17:36,073][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:17:36,576][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:17:37,080][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:17:37,583][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:17:38,085][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:17:38,586][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:17:39,089][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:17:39,591][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:17:40,093][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:17:40,596][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:17:41,097][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:17:41,601][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:17:42,102][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:17:42,604][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:17:43,105][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:17:43,607][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:17:44,109][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:17:44,611][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:17:45,113][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:17:45,615][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:17:46,115][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:17:46,617][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:17:47,119][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:17:47,621][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:17:48,122][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:17:48,626][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:17:49,127][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:17:49,629][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:17:50,130][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:17:50,633][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:17:51,135][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:17:51,636][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:17:52,137][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:17:52,639][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:17:53,142][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:17:53,643][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:17:54,144][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:17:54,645][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:17:55,146][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:17:55,648][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:17:56,151][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:17:56,654][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:17:57,157][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:17:57,659][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:17:58,160][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:17:58,661][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:17:59,164][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:17:59,666][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:18:00,167][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:18:00,670][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:18:01,175][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:18:01,678][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:18:02,180][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:18:02,682][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:18:03,184][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:18:03,684][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:18:04,184][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:18:04,684][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:18:05,184][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:18:05,684][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:18:06,184][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:18:06,684][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:18:07,186][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:18:07,688][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:18:08,189][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:18:08,691][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:18:09,194][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:18:09,696][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:18:10,198][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:18:10,700][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:18:11,202][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:18:11,705][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:18:12,206][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:18:12,708][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:18:13,209][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:18:13,710][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:18:14,212][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:18:14,716][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:18:15,218][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:18:15,719][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:18:16,221][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:18:16,723][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:18:17,224][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:18:17,725][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:18:18,226][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:18:18,728][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:18:19,229][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:18:19,731][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:18:20,232][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:18:20,736][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:18:21,237][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:18:21,739][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:18:22,240][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:18:22,741][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:18:23,243][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:18:23,745][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:18:24,246][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:18:24,747][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:18:25,249][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:18:25,750][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:18:26,251][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:18:26,753][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:18:27,255][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:18:27,756][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:18:28,257][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:18:28,758][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:18:29,260][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:18:29,761][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:18:30,266][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:18:30,767][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:18:31,269][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:18:31,771][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:18:32,271][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:18:32,774][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:18:33,276][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:18:33,778][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:18:34,281][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:18:34,783][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:18:35,282][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:18:35,782][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:18:36,282][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:18:36,782][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:18:37,283][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:18:37,784][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:18:38,283][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:18:38,783][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 02:18:39,408][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:04 [2026-03-26 02:18:40,158][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:18:40,161][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:18:40,162][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:18:40,826][__main__][INFO] - Iteration 495 took 1m 14s (8.80% Gen, 90.30% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 8m 40s. Estimated total time: 61h 52m 7s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 44s, 500 more iterations: 10h 18m 41s. [2026-03-26 02:18:40,828][__main__][INFO] - Starting iteration 495. [2026-03-26 02:18:41,226][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:18:41,227][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:18:41,847][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:18:42,994][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:18:48,951][__main__][INFO] - Number of regex retries in iteration 495: 2 [2026-03-26 02:18:48,952][__main__][INFO] - agents played in iteration 495 are Bob, Alice [2026-03-26 02:18:49,858][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:18:50,443][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:18:50,902][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:18:51,410][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:18:51,915][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:18:52,420][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:18:52,923][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:18:53,426][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:18:53,929][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:18:54,433][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:18:54,936][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:18:55,439][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:18:55,942][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:18:56,445][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:18:56,948][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:18:57,451][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:18:57,953][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:18:58,456][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:18:58,958][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:18:59,461][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:18:59,963][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:19:00,465][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:19:00,967][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:19:01,469][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:19:01,971][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:19:02,474][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:19:02,977][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:19:03,478][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:19:03,981][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:19:04,483][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:19:04,985][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:19:05,488][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:19:05,989][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:19:06,492][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:19:06,995][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:19:07,499][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:19:08,002][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:19:08,505][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:19:09,007][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:19:09,509][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:19:10,012][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:19:10,516][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:19:11,020][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:19:11,524][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:19:12,026][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:19:12,529][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:19:13,033][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:19:13,537][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:19:14,039][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:19:14,542][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:19:15,044][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:19:15,548][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:19:16,050][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:19:16,554][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:19:17,057][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:19:17,560][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:19:18,063][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:19:18,565][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:19:19,067][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:19:19,567][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:19:20,067][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:19:20,568][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:19:21,068][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:19:21,569][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:19:22,070][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:19:22,571][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:19:23,073][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:19:23,577][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:19:24,080][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:19:24,583][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:19:25,086][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:19:25,589][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:19:26,091][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:19:26,594][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:19:27,097][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:19:27,599][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:19:28,101][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:19:28,603][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:19:29,104][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:19:29,606][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:19:30,108][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:19:30,610][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:19:31,112][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:19:31,614][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:19:32,116][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:19:32,619][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:19:33,120][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:19:33,623][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:19:34,124][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:19:34,626][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:19:35,127][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:19:35,629][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:19:36,131][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:19:36,634][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:19:37,137][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:19:37,638][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:19:38,141][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:19:38,644][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:19:39,146][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:19:39,648][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:19:40,150][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:19:40,652][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:19:41,154][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:19:41,659][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:19:42,162][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:19:42,665][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:19:43,170][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:19:43,672][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:19:44,175][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:19:44,678][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:19:45,180][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:19:45,683][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:19:46,185][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:19:46,687][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:19:47,189][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:19:47,692][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:19:48,194][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:19:48,698][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:19:49,200][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:19:49,703][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:19:50,205][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:19:50,708][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:19:51,208][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:19:51,708][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:19:52,208][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:19:52,709][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:19:53,210][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:19:53,710][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:19:54,211][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:19:54,711][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21749 tokens. [2026-03-26 02:19:55,317][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-26 02:19:56,054][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:19:56,057][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:19:56,058][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:19:56,801][__main__][INFO] - Iteration 496 took 1m 15s (10.22% Gen, 88.79% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 14m 1s. Estimated total time: 62h 58m 45s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 57s, 500 more iterations: 10h 29m 47s. [2026-03-26 02:19:56,803][__main__][INFO] - Starting iteration 496. [2026-03-26 02:19:57,200][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:19:57,201][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:19:57,802][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:19:57,805][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:20:04,199][__main__][INFO] - Number of regex retries in iteration 496: 2 [2026-03-26 02:20:04,200][__main__][INFO] - agents played in iteration 496 are Bob, Alice [2026-03-26 02:20:05,110][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:20:05,692][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:20:06,151][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:20:06,659][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:20:07,163][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:20:07,666][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:20:08,168][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:20:08,671][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:20:09,175][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:20:09,678][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:20:10,179][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:20:10,681][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:20:11,184][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:20:11,686][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:20:12,187][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:20:12,689][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:20:13,189][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:20:13,691][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:20:14,193][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:20:14,698][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:20:15,200][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:20:15,702][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:20:16,205][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:20:16,706][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:20:17,208][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:20:17,711][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:20:18,214][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:20:18,716][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:20:19,219][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:20:19,721][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:20:20,223][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:20:20,724][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:20:21,227][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:20:21,729][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:20:22,232][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:20:22,735][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:20:23,237][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:20:23,740][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:20:24,243][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:20:24,745][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:20:25,247][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:20:25,751][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:20:26,254][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:20:26,757][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:20:27,260][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:20:27,762][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:20:28,264][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:20:28,765][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:20:29,267][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:20:29,770][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:20:30,272][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:20:30,773][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:20:31,274][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:20:31,777][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:20:32,278][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:20:32,780][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:20:33,282][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:20:33,783][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:20:34,284][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:20:34,786][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:20:35,287][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:20:35,789][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:20:36,291][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:20:36,793][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:20:37,296][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:20:37,798][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:20:38,302][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:20:38,804][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:20:39,307][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:20:39,810][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:20:40,317][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:20:40,820][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:20:41,326][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:20:41,831][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:20:42,333][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:20:42,839][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:20:43,343][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:20:43,845][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:20:44,349][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:20:44,851][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:20:45,354][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:20:45,856][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:20:46,359][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:20:46,862][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:20:47,364][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:20:47,866][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:20:48,368][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:20:48,871][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:20:49,374][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:20:49,877][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:20:50,379][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:20:50,882][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:20:51,385][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:20:51,888][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:20:52,390][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:20:52,893][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:20:53,395][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:20:53,898][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:20:54,400][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:20:54,902][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:20:55,404][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:20:55,906][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:20:56,407][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:20:56,910][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:20:57,413][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:20:57,916][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:20:58,418][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:20:58,918][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:20:59,421][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:20:59,923][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:21:00,424][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:21:00,924][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:21:01,425][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:21:01,924][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:21:02,425][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:21:02,926][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:21:03,428][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:21:03,930][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:21:04,432][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:21:04,933][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:21:05,437][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:21:05,939][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:21:06,440][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:21:06,942][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:21:07,444][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:21:07,945][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:21:08,446][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:21:08,949][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:21:09,450][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:21:09,952][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-26 02:21:10,564][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-26 02:21:11,298][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:21:11,301][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:21:11,302][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:21:11,947][__main__][INFO] - Iteration 497 took 1m 14s (9.36% Gen, 89.77% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 31m 24s. Estimated total time: 62h 17m 23s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 34s, 500 more iterations: 10h 22m 53s. [2026-03-26 02:21:11,950][__main__][INFO] - Starting iteration 497. [2026-03-26 02:21:12,348][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:21:12,349][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:21:20,118][__main__][INFO] - Number of regex retries in iteration 497: 0 [2026-03-26 02:21:20,119][__main__][INFO] - agents played in iteration 497 are Bob, Alice [2026-03-26 02:21:21,020][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:21:21,599][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:21:22,057][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:21:22,564][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:21:23,065][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:21:23,566][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:21:24,067][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:21:24,568][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:21:25,070][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:21:25,571][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:21:26,073][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:21:26,573][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:21:27,076][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:21:27,577][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:21:28,079][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:21:28,581][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:21:29,081][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:21:29,583][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:21:30,082][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:21:30,582][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:21:31,082][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:21:31,583][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:21:32,084][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:21:32,583][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:21:33,083][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:21:33,583][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:21:34,087][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:21:34,589][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:21:35,090][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:21:35,591][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:21:36,093][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:21:36,596][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:21:37,098][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:21:37,601][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:21:38,102][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:21:38,604][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:21:39,104][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:21:39,605][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:21:40,106][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:21:40,608][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:21:41,109][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:21:41,612][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:21:42,114][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:21:42,617][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:21:43,119][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:21:43,621][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:21:44,126][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:21:44,629][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:21:45,133][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:21:45,637][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:21:46,139][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:21:46,642][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:21:47,144][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:21:47,645][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:21:48,147][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:21:48,650][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:21:49,153][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:21:49,654][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:21:50,156][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:21:50,657][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:21:51,158][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:21:51,660][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:21:52,161][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:21:52,662][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:21:53,163][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:21:53,664][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:21:54,165][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:21:54,666][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:21:55,167][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:21:55,669][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:21:56,170][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:21:56,671][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:21:57,173][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:21:57,675][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:21:58,176][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:21:58,676][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:21:59,177][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:21:59,678][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:22:00,179][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:22:00,681][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:22:01,182][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:22:01,683][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:22:02,182][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:22:02,682][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:22:03,182][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:22:03,682][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:22:04,182][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:22:04,681][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:22:05,182][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:22:05,682][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:22:06,185][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:22:06,686][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:22:07,193][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:22:07,697][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:22:08,199][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:22:08,701][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:22:09,202][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:22:09,705][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:22:10,206][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:22:10,708][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:22:11,211][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:22:11,715][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:22:12,216][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:22:12,719][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:22:13,221][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:22:13,723][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:22:14,226][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:22:14,726][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:22:15,228][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:22:15,731][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:22:16,233][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:22:16,737][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:22:17,239][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:22:17,742][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:22:18,245][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:22:18,747][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:22:19,250][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:22:19,751][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:22:20,253][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:22:20,754][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:22:21,257][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:22:21,759][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:22:22,260][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:22:22,762][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:22:23,263][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:22:23,764][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:22:24,265][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:22:24,765][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:22:25,267][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:22:25,768][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21748 tokens. [2026-03-26 02:22:26,380][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.24%, ΔTime: 00:01:04 [2026-03-26 02:22:27,118][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:22:27,120][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:22:27,122][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:22:27,772][__main__][INFO] - Iteration 498 took 1m 15s (10.30% Gen, 88.83% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 4m 0s. Estimated total time: 62h 51m 14s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 42s, 500 more iterations: 10h 28m 32s. [2026-03-26 02:22:27,774][__main__][INFO] - Starting iteration 498. [2026-03-26 02:22:28,173][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:22:28,174][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:22:28,765][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:22:36,069][__main__][INFO] - Number of regex retries in iteration 498: 1 [2026-03-26 02:22:36,070][__main__][INFO] - agents played in iteration 498 are Bob, Alice [2026-03-26 02:22:36,986][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:22:37,562][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:22:38,020][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:22:38,526][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:22:39,027][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:22:39,529][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:22:40,031][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:22:40,534][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:22:41,036][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:22:41,541][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:22:42,043][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:22:42,545][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:22:43,047][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:22:43,548][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:22:44,048][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:22:44,548][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:22:45,053][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:22:45,556][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:22:46,058][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:22:46,560][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:22:47,062][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:22:47,564][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:22:48,064][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:22:48,565][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:22:49,068][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:22:49,569][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:22:50,070][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:22:50,570][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:22:51,070][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:22:51,570][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:22:52,072][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:22:52,573][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:22:53,073][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:22:53,575][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:22:54,077][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:22:54,578][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:22:55,080][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:22:55,581][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:22:56,083][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:22:56,584][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:22:57,085][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:22:57,586][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:22:58,089][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:22:58,591][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:22:59,093][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:22:59,596][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:23:00,099][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:23:00,601][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:23:01,104][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:23:01,607][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:23:02,107][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:23:02,607][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:23:03,107][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:23:03,607][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:23:04,108][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:23:04,609][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:23:05,110][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:23:05,610][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:23:06,111][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:23:06,615][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:23:07,117][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:23:07,619][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:23:08,120][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:23:08,621][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:23:09,122][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:23:09,624][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:23:10,126][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:23:10,628][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:23:11,129][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:23:11,631][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:23:12,133][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:23:12,638][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:23:13,140][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:23:13,643][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:23:14,145][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:23:14,647][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:23:15,148][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:23:15,650][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:23:16,152][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:23:16,654][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:23:17,156][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:23:17,658][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:23:18,160][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:23:18,663][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:23:19,165][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:23:19,667][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:23:20,168][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:23:20,670][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:23:21,171][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:23:21,673][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:23:22,176][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:23:22,677][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:23:23,179][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:23:23,681][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:23:24,182][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:23:24,684][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:23:25,186][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:23:25,688][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:23:26,190][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:23:26,692][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:23:27,195][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:23:27,698][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:23:28,200][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:23:28,703][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:23:29,205][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:23:29,706][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:23:30,208][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:23:30,711][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:23:31,214][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:23:31,718][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:23:32,222][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:23:32,724][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:23:33,227][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:23:33,731][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:23:34,233][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:23:34,734][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:23:35,237][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:23:35,740][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:23:36,242][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:23:36,744][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:23:37,250][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:23:37,752][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:23:38,257][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:23:38,760][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:23:39,263][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:23:39,765][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:23:40,267][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:23:40,770][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:23:41,274][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:23:41,777][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21734 tokens. [2026-03-26 02:23:42,392][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-26 02:23:43,143][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:23:43,145][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:23:43,147][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:23:43,806][__main__][INFO] - Iteration 499 took 1m 15s (10.44% Gen, 88.69% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 13m 10s. Estimated total time: 63h 1m 40s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 3s, 500 more iterations: 10h 30m 16s. [2026-03-26 02:23:43,808][__main__][INFO] - Starting iteration 499. [2026-03-26 02:23:44,208][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:23:44,208][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:23:44,796][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:23:52,234][__main__][INFO] - Number of regex retries in iteration 499: 1 [2026-03-26 02:23:52,235][__main__][INFO] - agents played in iteration 499 are Bob, Alice [2026-03-26 02:23:53,141][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:23:53,718][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:23:54,174][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:23:54,680][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:23:55,182][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:23:55,684][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:23:56,185][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:23:56,685][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:23:57,187][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:23:57,689][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:23:58,193][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:23:58,697][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:23:59,200][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:23:59,702][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:24:00,205][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:24:00,706][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:24:01,208][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:24:01,711][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:24:02,213][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:24:02,715][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:24:03,218][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:24:03,720][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:24:04,222][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:24:04,724][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:24:05,227][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:24:05,729][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:24:06,231][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:24:06,734][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:24:07,238][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:24:07,741][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:24:08,244][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:24:08,746][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:24:09,249][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:24:09,752][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:24:10,255][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:24:10,759][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:24:11,264][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:24:11,768][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:24:12,270][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:24:12,774][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:24:13,277][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:24:13,779][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:24:14,282][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:24:14,784][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:24:15,287][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:24:15,789][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:24:16,290][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:24:16,793][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:24:17,295][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:24:17,798][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:24:18,303][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:24:18,807][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:24:19,309][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:24:19,813][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:24:20,317][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:24:20,819][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:24:21,323][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:24:21,826][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:24:22,328][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:24:22,830][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:24:23,335][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:24:23,838][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:24:24,340][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:24:24,843][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:24:25,345][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:24:25,847][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:24:26,349][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:24:26,851][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:24:27,354][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:24:27,856][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:24:28,358][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:24:28,861][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:24:29,363][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:24:29,865][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:24:30,367][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:24:30,869][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:24:31,370][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:24:31,872][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:24:32,375][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:24:32,877][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:24:33,379][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:24:33,881][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:24:34,382][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:24:34,884][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:24:35,386][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:24:35,888][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:24:36,390][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:24:36,892][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:24:37,394][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:24:37,897][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:24:38,399][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:24:38,901][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:24:39,403][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:24:39,905][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:24:40,407][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:24:40,908][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:24:41,413][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:24:41,917][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:24:42,419][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:24:42,921][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:24:43,424][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:24:43,925][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:24:44,427][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:24:44,928][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:24:45,430][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:24:45,932][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:24:46,437][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:24:46,939][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:24:47,443][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:24:47,945][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:24:48,451][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:24:48,958][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:24:49,461][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:24:49,965][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:24:50,468][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:24:50,970][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:24:51,474][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:24:51,977][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:24:52,480][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:24:52,984][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:24:53,486][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:24:53,989][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:24:54,491][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:24:54,994][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:24:55,496][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:24:55,999][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:24:56,501][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:24:57,004][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:24:57,506][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:24:58,008][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21698 tokens. [2026-03-26 02:24:58,630][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-26 02:24:59,371][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:24:59,373][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:24:59,375][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:25:00,181][__main__][INFO] - Iteration 500 took 1m 15s (10.57% Gen, 88.37% Train). Generation: 8s, Training: 1m 7s. Estimated remaining time: 52h 28m 53s. Estimated total time: 63h 18m 40s. Time estimates for 10 more iterations: 12m 39s, 100 more iterations: 2h 6m 37s, 500 more iterations: 10h 33m 6s. [2026-03-26 02:25:00,183][__main__][INFO] - Starting iteration 500. [2026-03-26 02:25:00,583][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 9 and human policies 1. [2026-03-26 02:25:00,584][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:25:06,921][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:25:07,965][__main__][INFO] - Number of regex retries in iteration 500: 1 [2026-03-26 02:25:07,965][__main__][INFO] - agents played in iteration 500 are Bob, Alice [2026-03-26 02:25:08,874][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:25:09,461][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:25:09,920][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:25:10,426][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:25:10,929][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:25:11,434][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:25:11,938][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:25:12,441][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:25:12,944][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:25:13,446][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:25:13,945][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:25:14,444][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:25:14,943][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:25:15,441][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:25:15,941][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:25:16,440][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:25:16,939][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:25:17,439][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:25:17,943][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:25:18,445][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:25:18,947][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:25:19,449][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:25:19,951][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:25:20,454][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:25:20,957][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:25:21,459][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:25:21,961][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:25:22,464][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:25:22,965][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:25:23,467][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:25:23,968][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:25:24,470][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:25:24,972][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:25:25,474][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:25:25,981][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:25:26,486][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:25:26,991][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:25:27,495][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:25:28,001][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:25:28,505][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:25:29,010][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:25:29,516][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:25:30,019][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:25:30,523][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:25:31,025][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:25:31,528][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:25:32,031][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:25:32,534][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:25:33,038][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:25:33,541][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:25:34,046][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:25:34,549][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:25:35,053][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:25:35,556][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:25:36,059][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:25:36,563][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:25:37,066][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:25:37,571][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:25:38,076][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:25:38,579][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:25:39,083][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:25:39,588][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:25:40,091][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:25:40,593][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:25:41,098][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:25:41,604][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:25:42,107][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:25:42,609][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:25:43,111][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:25:43,613][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:25:44,119][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:25:44,622][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:25:45,124][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:25:45,626][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:25:46,125][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:25:46,623][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:25:47,122][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:25:47,622][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:25:48,120][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:25:48,619][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:25:49,120][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:25:49,621][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:25:50,125][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:25:50,627][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:25:51,130][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:25:51,633][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:25:52,135][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:25:52,638][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:25:53,141][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:25:53,644][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:25:54,146][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:25:54,648][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:25:55,152][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:25:55,654][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:25:56,158][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:25:56,659][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:25:57,161][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:25:57,664][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:25:58,168][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:25:58,675][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:25:59,180][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:25:59,684][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:26:00,190][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:26:00,695][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:26:01,200][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:26:01,705][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:26:02,208][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:26:02,710][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:26:03,214][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:26:03,719][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:26:04,222][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:26:04,725][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:26:05,228][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:26:05,731][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:26:06,235][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:26:06,739][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:26:07,243][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:26:07,746][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:26:08,248][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:26:08,751][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:26:09,255][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:26:09,760][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:26:10,265][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:26:10,768][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:26:11,273][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:26:11,777][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:26:12,280][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:26:12,783][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:26:13,285][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:26:13,788][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 02:26:14,402][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.66%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:04 [2026-03-26 02:26:15,134][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:26:15,137][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:26:15,138][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:26:16,371][__main__][INFO] - Iteration 501 took 1m 15s (9.74% Gen, 88.63% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 52h 18m 20s. Estimated total time: 63h 9m 24s. Time estimates for 10 more iterations: 12m 37s, 100 more iterations: 2h 6m 18s, 500 more iterations: 10h 31m 34s. [2026-03-26 02:26:16,373][__main__][INFO] - Starting iteration 501. [2026-03-26 02:26:16,773][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:26:16,774][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:26:18,505][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:26:23,199][__main__][INFO] - Number of regex retries in iteration 501: 1 [2026-03-26 02:26:23,200][__main__][INFO] - agents played in iteration 501 are Bob, Alice [2026-03-26 02:26:24,103][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:26:24,677][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:26:25,135][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:26:25,641][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:26:26,142][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:26:26,642][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:26:27,143][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:26:27,644][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:26:28,145][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:26:28,646][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:26:29,147][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:26:29,646][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:26:30,146][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:26:30,645][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:26:31,144][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:26:31,644][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:26:32,144][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:26:32,645][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:26:33,145][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:26:33,646][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:26:34,146][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:26:34,647][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:26:35,147][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:26:35,647][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:26:36,148][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:26:36,649][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:26:37,153][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:26:37,653][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:26:38,155][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:26:38,656][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:26:39,157][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:26:39,658][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:26:40,158][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:26:40,659][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:26:41,161][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:26:41,664][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:26:42,165][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:26:42,666][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:26:43,167][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:26:43,667][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:26:44,167][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:26:44,668][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:26:45,171][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:26:45,672][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:26:46,174][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:26:46,676][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:26:47,179][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:26:47,681][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:26:48,183][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:26:48,685][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:26:49,185][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:26:49,687][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:26:50,187][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:26:50,688][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:26:51,191][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:26:51,692][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:26:52,192][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:26:52,694][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:26:53,197][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:26:53,698][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:26:54,199][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:26:54,699][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:26:55,200][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:26:55,701][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:26:56,202][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:26:56,702][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:26:57,203][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:26:57,703][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:26:58,204][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:26:58,704][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:26:59,204][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:26:59,703][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:27:00,204][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:27:00,704][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:27:01,204][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:27:01,704][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:27:02,204][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:27:02,703][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:27:03,202][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:27:03,702][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:27:04,203][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:27:04,703][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:27:05,203][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:27:05,703][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:27:06,203][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:27:06,703][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:27:07,203][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:27:07,704][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:27:08,205][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:27:08,705][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:27:09,205][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:27:09,705][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:27:10,205][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:27:10,706][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:27:11,208][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:27:11,711][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:27:12,211][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:27:12,712][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:27:13,213][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:27:13,716][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:27:14,217][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:27:14,719][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:27:15,220][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:27:15,722][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:27:16,223][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:27:16,724][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:27:17,226][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:27:17,727][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:27:18,228][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:27:18,730][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:27:19,231][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:27:19,733][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:27:20,236][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:27:20,739][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:27:21,239][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:27:21,740][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:27:22,241][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:27:22,742][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:27:23,242][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:27:23,743][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:27:24,244][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:27:24,745][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:27:25,246][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:27:25,746][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:27:26,247][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:27:26,748][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:27:27,249][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:27:27,750][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:27:28,251][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:27:28,751][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21760 tokens. [2026-03-26 02:27:29,362][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-26 02:27:30,094][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:27:30,096][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:27:30,098][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:27:30,749][__main__][INFO] - Iteration 502 took 1m 13s (8.69% Gen, 90.43% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 50h 46m 32s. Estimated total time: 61h 38m 49s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 17s, 500 more iterations: 10h 16m 28s. [2026-03-26 02:27:30,751][__main__][INFO] - Starting iteration 502. [2026-03-26 02:27:31,151][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:27:31,152][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:27:38,065][__main__][INFO] - Number of regex retries in iteration 502: 0 [2026-03-26 02:27:38,066][__main__][INFO] - agents played in iteration 502 are Bob, Alice [2026-03-26 02:27:38,973][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:27:39,815][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:27:40,272][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:27:40,778][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:27:41,282][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:27:41,784][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:27:42,285][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:27:42,786][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:27:43,287][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:27:43,787][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:27:44,290][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:27:44,792][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:27:45,294][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:27:45,795][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:27:46,296][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:27:46,797][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:27:47,298][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:27:47,799][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:27:48,302][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:27:48,805][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:27:49,305][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:27:49,806][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:27:50,306][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:27:50,807][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:27:51,309][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:27:51,813][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:27:52,315][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:27:52,817][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:27:53,318][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:27:53,819][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:27:54,322][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:27:54,824][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:27:55,325][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:27:55,826][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:27:56,324][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:27:56,823][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:27:57,322][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:27:57,822][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:27:58,321][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:27:58,820][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:27:59,319][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:27:59,817][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:28:00,320][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:28:00,820][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:28:01,321][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:28:01,822][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:28:02,323][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:28:02,824][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:28:03,324][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:28:03,824][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:28:04,325][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:28:04,825][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:28:05,326][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:28:05,827][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:28:06,327][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:28:06,829][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:28:07,333][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:28:07,837][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:28:08,340][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:28:08,843][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:28:09,345][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:28:09,848][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:28:10,350][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:28:10,854][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:28:11,359][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:28:11,863][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:28:12,365][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:28:12,866][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:28:13,368][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:28:13,871][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:28:14,372][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:28:14,874][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:28:15,374][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:28:15,877][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:28:16,379][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:28:16,881][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:28:17,382][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:28:17,883][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:28:18,384][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:28:18,885][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:28:19,386][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:28:19,887][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:28:20,389][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:28:20,891][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:28:21,393][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:28:21,896][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:28:22,398][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:28:22,899][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:28:23,401][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:28:23,903][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:28:24,404][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:28:24,906][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:28:25,407][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:28:25,909][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:28:26,411][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:28:26,913][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:28:27,415][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:28:27,918][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:28:28,418][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:28:28,918][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:28:29,418][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:28:29,917][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:28:30,418][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:28:30,918][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:28:31,421][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:28:31,921][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:28:32,424][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:28:32,925][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:28:33,425][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:28:33,926][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:28:34,427][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:28:34,928][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:28:35,428][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:28:35,929][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:28:36,431][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:28:36,931][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:28:37,432][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:28:37,934][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:28:38,436][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:28:38,938][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:28:39,440][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:28:39,941][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:28:40,444][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:28:40,947][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:28:41,452][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:28:41,955][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:28:42,456][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:28:42,958][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:28:43,460][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:28:43,962][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21745 tokens. [2026-03-26 02:28:44,629][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-26 02:28:45,371][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:28:45,373][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:28:45,375][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:28:46,048][__main__][INFO] - Iteration 503 took 1m 14s (9.23% Gen, 89.87% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 31m 19s. Estimated total time: 62h 24m 51s. Time estimates for 10 more iterations: 12m 28s, 100 more iterations: 2h 4m 49s, 500 more iterations: 10h 24m 8s. [2026-03-26 02:28:46,050][__main__][INFO] - Starting iteration 503. [2026-03-26 02:28:46,450][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:28:46,450][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:28:49,405][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:28:53,821][__main__][INFO] - Number of regex retries in iteration 503: 1 [2026-03-26 02:28:53,821][__main__][INFO] - agents played in iteration 503 are Bob, Alice [2026-03-26 02:28:54,732][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:28:55,431][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:28:55,918][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:28:56,425][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:28:56,925][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:28:57,425][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:28:57,923][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:28:58,423][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:28:58,923][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:28:59,423][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:28:59,927][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:29:00,429][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:29:00,930][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:29:01,432][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:29:01,937][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:29:02,439][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:29:02,941][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:29:03,443][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:29:03,944][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:29:04,445][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:29:04,946][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:29:05,447][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:29:05,949][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:29:06,450][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:29:06,950][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:29:07,451][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:29:07,952][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:29:08,454][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:29:08,956][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:29:09,458][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:29:09,960][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:29:10,462][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:29:10,964][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:29:11,469][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:29:11,972][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:29:12,474][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:29:12,977][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:29:13,480][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:29:13,982][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:29:14,486][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:29:14,987][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:29:15,489][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:29:15,990][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:29:16,492][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:29:16,993][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:29:17,495][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:29:17,996][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:29:18,498][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:29:18,999][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:29:19,501][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:29:20,002][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:29:20,504][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:29:21,004][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:29:21,505][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:29:22,006][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:29:22,506][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:29:23,007][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:29:23,508][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:29:24,009][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:29:24,510][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:29:25,010][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:29:25,512][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:29:26,015][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:29:26,516][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:29:27,017][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:29:27,519][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:29:28,020][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:29:28,520][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:29:29,019][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:29:29,520][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:29:30,019][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:29:30,519][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:29:31,018][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:29:31,519][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:29:32,021][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:29:32,522][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:29:33,025][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:29:33,527][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:29:34,029][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:29:34,530][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:29:35,031][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:29:35,533][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:29:36,036][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:29:36,537][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:29:37,041][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:29:37,545][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:29:38,046][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:29:38,547][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:29:39,047][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:29:39,548][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:29:40,049][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:29:40,550][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:29:41,050][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:29:41,555][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:29:42,057][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:29:42,558][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:29:43,060][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:29:43,561][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:29:44,063][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:29:44,565][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:29:45,067][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:29:45,570][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:29:46,072][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:29:46,573][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:29:47,074][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:29:47,578][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:29:48,080][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:29:48,582][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:29:49,083][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:29:49,585][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:29:50,085][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:29:50,587][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:29:51,088][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:29:51,590][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:29:52,091][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:29:52,592][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:29:53,095][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:29:53,599][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:29:54,100][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:29:54,602][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:29:55,103][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:29:55,604][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:29:56,104][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:29:56,606][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:29:57,106][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:29:57,608][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:29:58,110][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:29:58,611][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:29:59,113][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:29:59,617][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 02:30:00,234][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.20%, ΔTime: 00:01:04 [2026-03-26 02:30:00,987][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:30:00,990][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:30:00,991][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:30:01,683][__main__][INFO] - Iteration 504 took 1m 15s (9.80% Gen, 89.28% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 46m 54s. Estimated total time: 62h 41m 42s. Time estimates for 10 more iterations: 12m 32s, 100 more iterations: 2h 5m 23s, 500 more iterations: 10h 26m 57s. [2026-03-26 02:30:01,687][__main__][INFO] - Starting iteration 504. [2026-03-26 02:30:02,085][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:30:02,086][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:30:05,961][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 balls, 1, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:30:08,949][__main__][INFO] - Number of regex retries in iteration 504: 1 [2026-03-26 02:30:08,950][__main__][INFO] - agents played in iteration 504 are Bob, Alice [2026-03-26 02:30:09,915][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:30:10,499][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:30:10,957][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:30:11,467][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:30:11,969][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:30:12,472][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:30:12,976][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:30:13,479][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:30:13,982][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:30:14,485][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:30:14,987][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:30:15,489][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:30:15,992][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:30:16,495][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:30:16,998][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:30:17,499][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:30:18,000][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:30:18,502][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:30:19,006][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:30:19,508][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:30:20,009][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:30:20,511][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:30:21,013][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:30:21,515][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:30:22,017][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:30:22,519][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:30:23,020][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:30:23,521][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:30:24,022][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:30:24,523][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:30:25,024][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:30:25,525][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:30:26,026][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:30:26,527][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:30:27,029][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:30:27,531][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:30:28,033][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:30:28,538][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:30:29,040][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:30:29,543][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:30:30,046][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:30:30,548][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:30:31,050][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:30:31,552][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:30:32,054][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:30:32,556][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:30:33,057][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:30:33,559][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:30:34,062][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:30:34,564][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:30:35,066][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:30:35,569][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:30:36,070][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:30:36,573][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:30:37,077][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:30:37,579][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:30:38,081][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:30:38,582][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:30:39,085][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:30:39,587][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:30:40,088][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:30:40,590][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:30:41,093][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:30:41,597][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:30:42,099][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:30:42,601][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:30:43,103][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:30:43,605][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:30:44,107][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:30:44,608][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:30:45,111][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:30:45,615][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:30:46,118][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:30:46,620][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:30:47,122][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:30:47,623][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:30:48,125][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:30:48,627][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:30:49,128][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:30:49,629][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:30:50,130][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:30:50,632][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:30:51,138][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:30:51,641][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:30:52,144][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:30:52,647][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:30:53,149][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:30:53,656][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:30:54,159][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:30:54,722][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:30:55,225][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:30:55,726][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:30:56,227][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:30:56,727][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:30:57,228][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:30:57,729][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:30:58,230][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:30:58,731][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:30:59,233][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:30:59,738][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:31:00,241][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:31:00,744][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:31:01,247][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:31:01,749][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:31:02,251][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:31:02,756][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:31:03,258][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:31:03,760][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:31:04,262][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:31:04,764][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:31:05,265][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:31:05,767][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:31:06,268][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:31:07,005][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:31:07,508][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:31:08,009][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:31:08,511][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:31:09,012][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:31:09,513][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:31:10,014][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:31:10,517][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:31:11,018][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:31:11,523][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:31:12,026][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:31:12,528][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:31:13,030][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:31:13,532][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:31:14,035][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:31:14,537][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:31:15,039][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21729 tokens. [2026-03-26 02:31:15,667][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:05 [2026-03-26 02:31:16,310][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:31:16,312][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:31:16,314][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:31:16,946][__main__][INFO] - Iteration 505 took 1m 14s (9.17% Gen, 89.98% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 27m 0s. Estimated total time: 62h 23m 4s. Time estimates for 10 more iterations: 12m 28s, 100 more iterations: 2h 4m 46s, 500 more iterations: 10h 23m 50s. [2026-03-26 02:31:16,950][__main__][INFO] - Starting iteration 505. [2026-03-26 02:31:17,348][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:31:17,349][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:31:21,976][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:31:22,675][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:31:24,162][__main__][INFO] - Number of regex retries in iteration 505: 2 [2026-03-26 02:31:24,163][__main__][INFO] - agents played in iteration 505 are Bob, Alice [2026-03-26 02:31:25,079][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:31:25,662][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:31:26,120][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:31:26,627][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:31:27,130][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:31:27,634][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:31:28,139][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:31:28,642][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:31:29,145][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:31:29,648][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:31:30,151][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:31:30,654][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:31:31,157][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:31:31,660][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:31:32,163][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:31:32,665][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:31:33,168][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:31:33,670][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:31:34,170][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:31:34,672][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:31:35,174][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:31:35,677][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:31:36,178][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:31:36,679][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:31:37,180][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:31:37,682][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:31:38,181][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:31:38,684][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:31:39,184][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:31:39,684][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:31:40,183][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:31:40,684][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:31:41,185][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:31:41,687][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:31:42,190][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:31:42,691][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:31:43,192][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:31:43,693][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:31:44,195][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:31:44,697][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:31:45,199][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:31:45,700][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:31:46,203][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:31:46,704][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:31:47,206][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:31:47,707][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:31:48,209][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:31:48,711][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:31:49,213][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:31:49,715][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:31:50,217][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:31:50,719][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:31:51,221][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:31:51,723][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:31:52,224][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:31:52,725][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:31:53,226][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:31:53,727][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:31:54,230][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:31:54,733][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:31:55,236][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:31:55,740][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:31:56,243][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:31:56,746][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:31:57,248][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:31:57,750][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:31:58,252][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:31:58,757][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:31:59,260][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:31:59,764][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:32:00,266][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:32:00,768][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:32:01,270][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:32:01,774][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:32:02,277][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:32:02,779][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:32:03,281][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:32:03,783][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:32:04,285][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:32:04,787][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:32:05,289][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:32:05,791][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:32:06,292][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:32:06,792][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:32:07,294][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:32:07,796][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:32:08,297][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:32:08,798][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:32:09,299][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:32:09,800][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:32:10,300][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:32:10,801][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:32:11,303][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:32:11,805][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:32:12,305][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:32:12,804][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:32:13,303][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:32:13,803][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:32:14,305][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:32:14,807][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:32:15,308][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:32:15,810][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:32:16,311][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:32:16,812][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:32:17,314][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:32:17,817][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:32:18,319][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:32:18,822][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:32:19,324][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:32:19,825][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:32:20,327][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:32:20,830][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:32:21,331][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:32:21,833][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:32:22,335][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:32:22,837][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:32:23,339][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:32:23,842][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:32:24,344][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:32:24,845][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:32:25,346][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:32:25,848][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:32:26,350][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:32:26,852][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:32:27,354][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:32:27,855][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:32:28,357][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:32:28,859][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:32:29,362][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:32:29,864][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 02:32:30,476][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-26 02:32:31,209][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:32:31,212][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:32:31,213][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:32:31,881][__main__][INFO] - Iteration 506 took 1m 14s (9.14% Gen, 89.96% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 9m 23s. Estimated total time: 62h 6m 42s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 13s, 500 more iterations: 10h 21m 7s. [2026-03-26 02:32:31,883][__main__][INFO] - Starting iteration 506. [2026-03-26 02:32:32,281][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:32:32,282][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:32:38,145][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:32:39,177][__main__][INFO] - Number of regex retries in iteration 506: 1 [2026-03-26 02:32:39,178][__main__][INFO] - agents played in iteration 506 are Bob, Alice [2026-03-26 02:32:40,093][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:32:40,680][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:32:41,137][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:32:41,644][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:32:42,144][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:32:42,645][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:32:43,145][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:32:43,645][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:32:44,145][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:32:44,645][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:32:45,148][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:32:45,653][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:32:46,156][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:32:46,659][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:32:47,163][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:32:47,665][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:32:48,169][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:32:48,673][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:32:49,174][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:32:49,675][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:32:50,176][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:32:50,677][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:32:51,178][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:32:51,679][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:32:52,179][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:32:52,680][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:32:53,182][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:32:53,684][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:32:54,186][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:32:54,688][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:32:55,191][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:32:55,695][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:32:56,199][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:32:56,700][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:32:57,203][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:32:57,704][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:32:58,205][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:32:58,705][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:32:59,206][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:32:59,707][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:33:00,207][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:33:00,707][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:33:01,209][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:33:01,711][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:33:02,214][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:33:02,719][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:33:03,224][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:33:03,727][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:33:04,232][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:33:04,735][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:33:05,240][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:33:05,742][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:33:06,245][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:33:06,748][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:33:07,250][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:33:07,751][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:33:08,253][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:33:08,756][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:33:09,258][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:33:09,759][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:33:10,260][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:33:10,762][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:33:11,266][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:33:11,768][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:33:12,268][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:33:12,770][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:33:13,271][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:33:13,771][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:33:14,271][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:33:14,771][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:33:15,272][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:33:15,774][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:33:16,275][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:33:16,776][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:33:17,278][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:33:17,781][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:33:18,283][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:33:18,787][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:33:19,290][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:33:19,793][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:33:20,294][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:33:20,797][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:33:21,298][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:33:21,799][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:33:22,299][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:33:22,800][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:33:23,300][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:33:23,801][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:33:24,302][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:33:24,802][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:33:25,304][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:33:25,806][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:33:26,307][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:33:26,810][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:33:27,312][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:33:27,815][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:33:28,318][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:33:28,821][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:33:29,322][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:33:29,822][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:33:30,323][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:33:30,823][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:33:31,323][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:33:31,824][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:33:32,324][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:33:32,824][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:33:33,326][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:33:33,826][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:33:34,327][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:33:34,827][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:33:35,327][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:33:35,828][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:33:36,328][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:33:36,829][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:33:37,330][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:33:37,832][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:33:38,334][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:33:38,837][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:33:39,339][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:33:39,841][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:33:40,345][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:33:40,846][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:33:41,349][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:33:41,851][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:33:42,353][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:33:42,855][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:33:43,357][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:33:43,858][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:33:44,359][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:33:44,861][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21590 tokens. [2026-03-26 02:33:45,483][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.54%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:04 [2026-03-26 02:33:46,217][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:33:46,219][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:33:46,221][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:33:46,916][__main__][INFO] - Iteration 507 took 1m 14s (9.24% Gen, 89.83% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 13m 14s. Estimated total time: 62h 11m 48s. Time estimates for 10 more iterations: 12m 26s, 100 more iterations: 2h 4m 23s, 500 more iterations: 10h 21m 58s. [2026-03-26 02:33:46,918][__main__][INFO] - Starting iteration 507. [2026-03-26 02:33:47,318][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:33:47,319][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:33:53,835][__main__][INFO] - Number of regex retries in iteration 507: 0 [2026-03-26 02:33:53,836][__main__][INFO] - agents played in iteration 507 are Bob, Alice [2026-03-26 02:33:54,744][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:33:55,327][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:33:55,786][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:33:56,292][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:33:56,794][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:33:57,299][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:33:57,801][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:33:58,304][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:33:58,805][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:33:59,306][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:33:59,810][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:34:00,312][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:34:00,813][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:34:01,316][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:34:01,819][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:34:02,322][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:34:02,824][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:34:03,326][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:34:03,826][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:34:04,325][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:34:04,825][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:34:05,325][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:34:05,826][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:34:06,326][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:34:06,827][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:34:07,329][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:34:07,832][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:34:08,334][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:34:08,836][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:34:09,337][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:34:09,838][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:34:10,340][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:34:10,841][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:34:11,346][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:34:11,849][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:34:12,351][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:34:12,852][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:34:13,355][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:34:13,857][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:34:14,359][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:34:14,862][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:34:15,364][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:34:15,866][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:34:16,366][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:34:16,866][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:34:17,367][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:34:17,868][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:34:18,369][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:34:18,870][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:34:19,370][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:34:19,870][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:34:20,371][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:34:20,871][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:34:21,371][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:34:21,871][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:34:22,371][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:34:22,871][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:34:23,371][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:34:23,873][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:34:24,375][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:34:24,877][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:34:25,378][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:34:25,880][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:34:26,382][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:34:26,883][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:34:27,385][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:34:27,886][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:34:28,387][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:34:28,890][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:34:29,392][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:34:29,894][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:34:30,395][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:34:30,897][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:34:31,399][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:34:31,900][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:34:32,402][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:34:32,904][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:34:33,406][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:34:33,907][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:34:34,409][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:34:34,910][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:34:35,413][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:34:35,915][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:34:36,416][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:34:36,916][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:34:37,417][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:34:37,918][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:34:38,418][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:34:38,918][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:34:39,419][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:34:39,920][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:34:40,422][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:34:40,922][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:34:41,426][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:34:41,928][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:34:42,429][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:34:42,931][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:34:43,431][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:34:43,933][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:34:44,436][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:34:44,940][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:34:45,442][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:34:45,945][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:34:46,447][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:34:46,948][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:34:47,451][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:34:47,952][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:34:48,453][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:34:48,954][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:34:49,455][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:34:49,955][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:34:50,456][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:34:50,957][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:34:51,457][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:34:51,958][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:34:52,459][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:34:52,959][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:34:53,460][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:34:53,960][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:34:54,461][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:34:54,962][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:34:55,463][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:34:55,965][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:34:56,466][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:34:56,967][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:34:57,469][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:34:57,973][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:34:58,477][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:34:58,981][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:34:59,483][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-26 02:35:00,105][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-26 02:35:00,846][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:35:00,848][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:35:00,849][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:35:01,504][__main__][INFO] - Iteration 508 took 1m 14s (8.78% Gen, 90.33% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 50h 49m 31s. Estimated total time: 61h 49m 19s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 38s, 500 more iterations: 10h 18m 13s. [2026-03-26 02:35:01,506][__main__][INFO] - Starting iteration 508. [2026-03-26 02:35:01,905][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:35:01,905][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:35:04,004][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:35:10,454][__main__][INFO] - Number of regex retries in iteration 508: 1 [2026-03-26 02:35:10,455][__main__][INFO] - agents played in iteration 508 are Bob, Alice [2026-03-26 02:35:11,373][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:35:11,956][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:35:12,415][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:35:12,946][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:35:13,450][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:35:13,952][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:35:14,454][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:35:14,956][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:35:15,458][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:35:15,960][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:35:16,462][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:35:16,964][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:35:17,466][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:35:17,967][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:35:18,473][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:35:18,976][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:35:19,478][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:35:19,980][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:35:20,480][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:35:20,981][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:35:21,482][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:35:21,983][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:35:22,484][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:35:22,984][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:35:23,485][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:35:23,986][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:35:24,487][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:35:24,984][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:35:25,486][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:35:25,987][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:35:26,488][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:35:26,988][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:35:27,487][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:35:27,989][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:35:28,488][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:35:28,989][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:35:29,489][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:35:29,991][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:35:30,491][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:35:30,992][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:35:31,492][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:35:31,993][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:35:32,496][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:35:32,998][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:35:33,500][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:35:34,001][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:35:34,503][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:35:35,005][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:35:35,506][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:35:36,008][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:35:36,508][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:35:37,011][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:35:37,516][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:35:38,018][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:35:38,519][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:35:39,021][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:35:39,523][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:35:40,025][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:35:40,525][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:35:41,027][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:35:41,528][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:35:42,029][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:35:42,528][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:35:43,028][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:35:43,527][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:35:44,027][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:35:44,530][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:35:45,032][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:35:45,534][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:35:46,037][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:35:46,540][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:35:47,042][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:35:47,545][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:35:48,046][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:35:48,549][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:35:49,052][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:35:49,557][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:35:50,060][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:35:50,563][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:35:51,065][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:35:51,567][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:35:52,069][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:35:52,571][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:35:53,072][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:35:53,574][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:35:54,075][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:35:54,576][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:35:55,078][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:35:55,578][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:35:56,079][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:35:56,580][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:35:57,079][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:35:57,580][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:35:58,080][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:35:58,581][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:35:59,083][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:35:59,584][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:36:00,085][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:36:00,586][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:36:01,086][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:36:01,586][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:36:02,086][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:36:02,586][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:36:03,086][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:36:03,587][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:36:04,088][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:36:04,591][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:36:05,093][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:36:05,596][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:36:06,098][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:36:06,600][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:36:07,102][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:36:07,605][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:36:08,106][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:36:08,609][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:36:09,111][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:36:09,613][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:36:10,116][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:36:10,621][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:36:11,124][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:36:11,627][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:36:12,130][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:36:12,631][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:36:13,131][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:36:13,631][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:36:14,132][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:36:14,632][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:36:15,129][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:36:15,628][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:36:16,128][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21721 tokens. [2026-03-26 02:36:16,741][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 02:36:17,476][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:36:17,478][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:36:17,480][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:36:18,218][__main__][INFO] - Iteration 509 took 1m 16s (11.20% Gen, 87.83% Train). Generation: 8s, Training: 1m 7s. Estimated remaining time: 52h 34m 35s. Estimated total time: 63h 35m 40s. Time estimates for 10 more iterations: 12m 43s, 100 more iterations: 2h 7m 11s, 500 more iterations: 10h 35m 56s. [2026-03-26 02:36:18,220][__main__][INFO] - Starting iteration 509. [2026-03-26 02:36:18,617][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:36:18,618][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:36:25,077][__main__][INFO] - Number of regex retries in iteration 509: 0 [2026-03-26 02:36:25,078][__main__][INFO] - agents played in iteration 509 are Bob, Alice [2026-03-26 02:36:26,265][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:36:26,845][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:36:27,302][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:36:27,808][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:36:28,308][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:36:28,808][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:36:29,309][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:36:29,809][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:36:30,310][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:36:30,811][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:36:31,314][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:36:31,818][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:36:32,320][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:36:32,824][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:36:33,326][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:36:33,829][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:36:34,331][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:36:34,836][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:36:35,340][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:36:35,843][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:36:36,346][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:36:36,848][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:36:37,350][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:36:37,853][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:36:38,356][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:36:38,859][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:36:39,360][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:36:39,863][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:36:40,365][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:36:40,867][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:36:41,372][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:36:41,874][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:36:42,376][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:36:42,879][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:36:43,379][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:36:43,880][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:36:44,380][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:36:44,881][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:36:45,381][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:36:45,882][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:36:46,383][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:36:46,883][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:36:47,385][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:36:47,885][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:36:48,386][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:36:48,887][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:36:49,388][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:36:49,889][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:36:50,389][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:36:50,890][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:36:51,392][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:36:51,893][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:36:52,395][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:36:52,898][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:36:53,400][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:36:53,902][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:36:54,404][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:36:54,905][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:36:55,405][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:36:55,905][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:36:56,405][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:36:56,905][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:36:57,405][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:36:57,905][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:36:58,405][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:36:58,904][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:36:59,405][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:36:59,906][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:37:00,409][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:37:00,910][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:37:01,413][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:37:01,915][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:37:02,416][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:37:02,918][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:37:03,420][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:37:03,922][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:37:04,424][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:37:04,926][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:37:05,428][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:37:05,930][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:37:06,433][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:37:06,937][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:37:07,442][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:37:07,946][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:37:08,449][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:37:08,951][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:37:09,453][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:37:09,955][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:37:10,457][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:37:10,960][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:37:11,464][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:37:11,966][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:37:12,468][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:37:12,969][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:37:13,469][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:37:13,971][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:37:14,472][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:37:14,973][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:37:15,474][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:37:15,974][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:37:16,474][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:37:16,976][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:37:17,477][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:37:17,978][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:37:18,479][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:37:18,980][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:37:19,480][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:37:19,982][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:37:20,483][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:37:20,984][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:37:21,485][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:37:21,986][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:37:22,486][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:37:22,987][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:37:23,489][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:37:23,991][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:37:24,492][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:37:24,994][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:37:25,496][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:37:25,998][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:37:26,500][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:37:27,002][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:37:27,503][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:37:28,003][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:37:28,504][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:37:29,003][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:37:29,504][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:37:30,004][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:37:30,504][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:37:31,004][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-26 02:37:31,618][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-26 02:37:32,359][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:37:32,361][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:37:32,363][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:37:33,006][__main__][INFO] - Iteration 510 took 1m 14s (8.68% Gen, 90.45% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 50h 57m 8s. Estimated total time: 61h 59m 27s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 58s, 500 more iterations: 10h 19m 54s. [2026-03-26 02:37:33,008][__main__][INFO] - Starting iteration 510. [2026-03-26 02:37:33,407][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:37:33,407][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:37:39,853][__main__][INFO] - Number of regex retries in iteration 510: 0 [2026-03-26 02:37:39,854][__main__][INFO] - agents played in iteration 510 are Bob, Alice [2026-03-26 02:37:40,776][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:37:41,361][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:37:41,819][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:37:42,325][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:37:42,827][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:37:43,327][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:37:43,828][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:37:44,328][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:37:44,829][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:37:45,331][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:37:45,831][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:37:46,332][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:37:46,832][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:37:47,332][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:37:47,833][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:37:48,337][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:37:48,839][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:37:49,339][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:37:49,843][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:37:50,345][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:37:50,847][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:37:51,349][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:37:51,851][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:37:52,354][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:37:52,855][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:37:53,357][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:37:53,857][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:37:54,358][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:37:54,859][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:37:55,360][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:37:55,860][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:37:56,361][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:37:56,862][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:37:57,363][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:37:57,867][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:37:58,369][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:37:58,871][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:37:59,373][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:37:59,875][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:38:00,377][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:38:00,879][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:38:01,384][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:38:01,888][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:38:02,392][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:38:02,894][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:38:03,397][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:38:03,899][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:38:04,401][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:38:04,903][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:38:05,404][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:38:05,905][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:38:06,406][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:38:06,908][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:38:07,408][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:38:07,909][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:38:08,409][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:38:08,910][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:38:09,411][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:38:09,913][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:38:10,415][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:38:10,917][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:38:11,422][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:38:11,925][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:38:12,427][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:38:12,930][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:38:13,432][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:38:13,933][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:38:14,437][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:38:14,938][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:38:15,440][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:38:15,942][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:38:16,443][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:38:16,944][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:38:17,444][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:38:17,946][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:38:18,446][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:38:18,948][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:38:19,448][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:38:19,948][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:38:20,448][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:38:20,948][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:38:21,448][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:38:21,949][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:38:22,451][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:38:22,953][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:38:23,454][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:38:23,956][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:38:24,458][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:38:24,960][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:38:25,462][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:38:25,963][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:38:26,464][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:38:26,965][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:38:27,466][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:38:27,967][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:38:28,468][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:38:28,970][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:38:29,470][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:38:29,972][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:38:30,473][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:38:30,976][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:38:31,479][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:38:31,981][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:38:32,483][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:38:32,985][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:38:33,487][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:38:33,989][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:38:34,491][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:38:34,992][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:38:35,494][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:38:35,995][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:38:36,499][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:38:37,004][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:38:37,508][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:38:38,011][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:38:38,512][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:38:39,012][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:38:39,514][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:38:40,016][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:38:40,517][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:38:41,019][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:38:41,523][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:38:42,026][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:38:42,528][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:38:43,030][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:38:43,532][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:38:44,034][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:38:44,537][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:38:45,040][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:38:45,543][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 02:38:46,158][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 02:38:46,895][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:38:46,897][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:38:46,899][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:38:47,545][__main__][INFO] - Iteration 511 took 1m 14s (8.69% Gen, 90.43% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 50h 43m 22s. Estimated total time: 61h 46m 56s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 33s, 500 more iterations: 10h 17m 49s. [2026-03-26 02:38:47,547][__main__][INFO] - Starting iteration 511. [2026-03-26 02:38:47,948][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:38:47,949][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:38:54,969][__main__][INFO] - Number of regex retries in iteration 511: 0 [2026-03-26 02:38:54,970][__main__][INFO] - agents played in iteration 511 are Bob, Alice [2026-03-26 02:38:55,881][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:38:56,461][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:38:56,919][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:38:57,425][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:38:57,926][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:38:58,427][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:38:58,927][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:38:59,429][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:38:59,928][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:39:00,429][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:39:00,929][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:39:01,429][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:39:01,931][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:39:02,432][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:39:02,934][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:39:03,435][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:39:03,936][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:39:04,437][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:39:04,942][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:39:05,445][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:39:05,947][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:39:06,448][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:39:06,951][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:39:07,452][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:39:07,955][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:39:08,457][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:39:08,959][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:39:09,461][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:39:09,964][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:39:10,466][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:39:10,969][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:39:11,473][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:39:11,975][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:39:12,478][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:39:12,979][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:39:13,480][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:39:13,980][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:39:14,480][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:39:14,981][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:39:15,482][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:39:15,983][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:39:16,485][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:39:16,986][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:39:17,486][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:39:17,988][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:39:18,490][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:39:18,992][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:39:19,495][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:39:19,995][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:39:20,496][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:39:20,999][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:39:21,501][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:39:22,004][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:39:22,505][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:39:23,006][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:39:23,507][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:39:24,008][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:39:24,508][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:39:25,011][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:39:25,513][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:39:26,014][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:39:26,517][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:39:27,019][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:39:27,522][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:39:28,025][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:39:28,528][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:39:29,029][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:39:29,530][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:39:30,031][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:39:30,532][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:39:31,033][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:39:31,535][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:39:32,036][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:39:32,538][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:39:33,039][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:39:33,539][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:39:34,040][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:39:34,540][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:39:35,040][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:39:35,540][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:39:36,041][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:39:36,541][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:39:37,044][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:39:37,546][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:39:38,048][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:39:38,550][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:39:39,051][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:39:39,553][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:39:40,057][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:39:40,559][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:39:41,061][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:39:41,566][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:39:42,067][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:39:42,569][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:39:43,071][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:39:43,573][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:39:44,074][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:39:44,576][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:39:45,078][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:39:45,579][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:39:46,081][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:39:46,582][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:39:47,083][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:39:47,584][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:39:48,085][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:39:48,586][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:39:49,086][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:39:49,587][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:39:50,087][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:39:50,588][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:39:51,090][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:39:51,590][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:39:52,091][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:39:52,592][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:39:53,093][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:39:53,596][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:39:54,098][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:39:54,599][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:39:55,100][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:39:55,602][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:39:56,103][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:39:56,604][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:39:57,106][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:39:57,608][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:39:58,109][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:39:58,611][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:39:59,113][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:39:59,615][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:40:00,118][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:40:00,620][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 02:40:01,234][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.65%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-26 02:40:01,969][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:40:01,971][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:40:01,972][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:40:02,690][__main__][INFO] - Iteration 512 took 1m 14s (9.39% Gen, 89.65% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 12m 16s. Estimated total time: 62h 17m 6s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 34s, 500 more iterations: 10h 22m 51s. [2026-03-26 02:40:02,692][__main__][INFO] - Starting iteration 512. [2026-03-26 02:40:03,093][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:40:03,094][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:40:06,733][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:40:10,199][__main__][INFO] - Number of regex retries in iteration 512: 1 [2026-03-26 02:40:10,200][__main__][INFO] - agents played in iteration 512 are Bob, Alice [2026-03-26 02:40:11,120][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:40:11,703][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:40:12,161][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:40:12,668][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:40:13,172][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:40:13,674][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:40:14,177][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:40:14,679][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:40:15,181][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:40:15,683][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:40:16,187][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:40:16,691][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:40:17,194][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:40:17,697][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:40:18,200][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:40:18,703][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:40:19,206][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:40:19,709][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:40:20,210][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:40:20,711][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:40:21,214][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:40:21,717][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:40:22,218][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:40:22,720][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:40:23,222][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:40:23,723][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:40:24,225][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:40:24,725][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:40:25,227][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:40:25,728][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:40:26,229][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:40:26,729][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:40:27,229][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:40:27,729][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:40:28,231][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:40:28,732][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:40:29,233][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:40:29,735][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:40:30,238][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:40:30,740][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:40:31,241][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:40:31,743][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:40:32,245][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:40:32,749][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:40:33,252][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:40:33,755][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:40:34,258][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:40:34,761][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:40:35,264][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:40:35,766][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:40:36,267][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:40:36,768][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:40:37,271][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:40:37,773][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:40:38,275][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:40:38,776][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:40:39,277][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:40:39,778][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:40:40,279][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:40:40,780][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:40:41,282][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:40:41,783][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:40:42,284][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:40:42,785][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:40:43,286][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:40:43,785][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:40:44,287][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:40:44,789][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:40:45,289][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:40:45,790][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:40:46,291][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:40:46,793][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:40:47,294][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:40:47,795][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:40:48,299][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:40:48,804][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:40:49,309][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:40:49,812][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:40:50,318][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:40:50,821][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:40:51,326][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:40:51,830][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:40:52,331][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:40:52,833][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:40:53,335][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:40:53,838][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:40:54,339][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:40:54,842][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:40:55,344][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:40:55,846][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:40:56,346][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:40:56,847][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:40:57,347][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:40:57,848][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:40:58,348][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:40:58,849][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:40:59,349][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:40:59,850][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:41:00,350][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:41:00,851][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:41:01,352][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:41:01,853][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:41:02,354][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:41:02,854][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:41:03,356][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:41:03,860][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:41:04,364][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:41:04,868][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:41:05,372][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:41:05,875][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:41:06,378][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:41:06,881][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:41:07,383][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:41:07,886][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:41:08,386][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:41:08,887][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:41:09,388][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:41:09,888][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:41:10,390][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:41:10,892][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:41:11,396][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:41:11,898][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:41:12,400][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:41:12,900][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:41:13,401][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:41:13,902][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:41:14,402][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:41:14,903][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:41:15,404][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:41:15,905][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-26 02:41:16,523][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.52%, ΔTime: 00:01:04 [2026-03-26 02:41:17,272][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:41:17,274][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:41:17,276][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:41:18,083][__main__][INFO] - Iteration 513 took 1m 14s (9.48% Gen, 89.45% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 23m 26s. Estimated total time: 62h 29m 31s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 59s, 500 more iterations: 10h 24m 55s. [2026-03-26 02:41:18,085][__main__][INFO] - Starting iteration 513. [2026-03-26 02:41:18,485][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:41:18,485][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:41:25,780][__main__][INFO] - Number of regex retries in iteration 513: 0 [2026-03-26 02:41:25,781][__main__][INFO] - agents played in iteration 513 are Bob, Alice [2026-03-26 02:41:26,695][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:41:27,281][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:41:27,739][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:41:28,247][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:41:28,748][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:41:29,250][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:41:29,752][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:41:30,254][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:41:30,756][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:41:31,257][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:41:31,758][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:41:32,260][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:41:32,761][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:41:33,263][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:41:33,764][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:41:34,266][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:41:34,767][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:41:35,268][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:41:35,772][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:41:36,275][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:41:36,778][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:41:37,284][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:41:37,787][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:41:38,289][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:41:38,791][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:41:39,294][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:41:39,795][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:41:40,296][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:41:40,797][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:41:41,303][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:41:41,806][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:41:42,307][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:41:42,808][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:41:43,309][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:41:43,810][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:41:44,312][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:41:44,815][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:41:45,316][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:41:45,819][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:41:46,321][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:41:46,823][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:41:47,325][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:41:47,828][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:41:48,330][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:41:48,832][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:41:49,335][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:41:49,840][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:41:50,342][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:41:50,845][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:41:51,348][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:41:51,849][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:41:52,351][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:41:52,852][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:41:53,355][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:41:53,857][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:41:54,359][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:41:54,862][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:41:55,364][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:41:55,866][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:41:56,369][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:41:56,871][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:41:57,373][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:41:57,875][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:41:58,379][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:41:58,881][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:41:59,384][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:41:59,885][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:42:00,386][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:42:00,887][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:42:01,388][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:42:01,889][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:42:02,391][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:42:02,892][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:42:03,393][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:42:03,893][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:42:04,397][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:42:04,900][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:42:05,403][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:42:05,905][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:42:06,407][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:42:06,907][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:42:07,408][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:42:07,910][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:42:08,412][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:42:08,914][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:42:09,416][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:42:09,918][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:42:10,422][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:42:10,925][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:42:11,429][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:42:11,930][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:42:12,431][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:42:12,932][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:42:13,435][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:42:13,937][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:42:14,439][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:42:14,940][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:42:15,442][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:42:15,944][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:42:16,446][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:42:16,947][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:42:17,448][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:42:17,949][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:42:18,451][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:42:18,952][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:42:19,454][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:42:19,956][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:42:20,459][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:42:20,960][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:42:21,462][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:42:21,964][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:42:22,467][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:42:22,970][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:42:23,472][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:42:23,973][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:42:24,473][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:42:24,975][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:42:25,477][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:42:25,979][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:42:26,481][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:42:26,982][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:42:27,483][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:42:27,985][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:42:28,487][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:42:28,989][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:42:29,491][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:42:29,992][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:42:30,493][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:42:30,997][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:42:31,500][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21750 tokens. [2026-03-26 02:42:32,116][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 02:42:32,852][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:42:32,854][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:42:32,855][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:42:33,678][__main__][INFO] - Iteration 514 took 1m 15s (9.70% Gen, 89.20% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 32m 20s. Estimated total time: 62h 39m 41s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 19s, 500 more iterations: 10h 26m 36s. [2026-03-26 02:42:33,680][__main__][INFO] - Starting iteration 514. [2026-03-26 02:42:34,080][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:42:34,080][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:42:35,399][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:42:40,955][__main__][INFO] - Number of regex retries in iteration 514: 1 [2026-03-26 02:42:40,956][__main__][INFO] - agents played in iteration 514 are Bob, Alice [2026-03-26 02:42:42,147][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:42:42,731][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:42:43,189][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:42:43,695][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:42:44,196][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:42:44,697][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:42:45,198][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:42:45,700][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:42:46,201][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:42:46,703][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:42:47,206][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:42:47,708][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:42:48,211][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:42:48,714][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:42:49,216][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:42:49,718][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:42:50,221][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:42:50,723][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:42:51,225][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:42:51,726][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:42:52,229][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:42:52,731][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:42:53,233][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:42:53,736][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:42:54,239][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:42:54,740][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:42:55,245][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:42:55,748][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:42:56,251][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:42:56,755][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:42:57,258][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:42:57,761][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:42:58,264][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:42:58,766][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:42:59,267][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:42:59,768][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:43:00,268][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:43:00,769][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:43:01,270][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:43:01,770][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:43:02,270][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:43:02,770][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:43:03,271][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:43:03,772][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:43:04,273][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:43:04,774][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:43:05,275][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:43:05,775][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:43:06,280][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:43:06,783][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:43:07,289][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:43:07,793][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:43:08,295][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:43:08,799][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:43:09,301][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:43:09,804][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:43:10,306][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:43:10,807][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:43:11,311][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:43:11,813][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:43:12,316][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:43:12,818][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:43:13,320][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:43:13,822][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:43:14,323][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:43:14,825][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:43:15,326][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:43:15,827][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:43:16,329][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:43:16,830][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:43:17,332][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:43:17,833][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:43:18,336][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:43:18,838][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:43:19,341][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:43:19,844][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:43:20,347][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:43:20,849][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:43:21,352][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:43:21,855][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:43:22,357][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:43:22,859][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:43:23,361][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:43:23,863][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:43:24,365][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:43:24,867][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:43:25,367][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:43:25,869][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:43:26,371][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:43:26,872][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:43:27,375][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:43:27,878][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:43:28,382][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:43:28,884][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:43:29,388][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:43:29,891][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:43:30,393][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:43:30,895][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:43:31,396][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:43:31,899][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:43:32,400][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:43:32,900][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:43:33,401][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:43:33,902][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:43:34,402][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:43:34,902][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:43:35,403][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:43:35,904][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:43:36,405][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:43:36,905][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:43:37,406][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:43:37,906][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:43:38,407][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:43:38,908][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:43:39,410][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:43:39,911][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:43:40,413][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:43:40,915][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:43:41,422][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:43:41,925][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:43:42,427][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:43:42,928][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:43:43,429][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:43:43,930][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:43:44,432][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:43:44,935][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:43:45,437][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:43:45,939][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:43:46,441][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:43:46,944][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 02:43:47,566][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-26 02:43:48,314][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:43:48,316][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:43:48,317][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:43:49,032][__main__][INFO] - Iteration 515 took 1m 14s (9.17% Gen, 89.87% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 19m 3s. Estimated total time: 62h 27m 38s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 55s, 500 more iterations: 10h 24m 36s. [2026-03-26 02:43:49,034][__main__][INFO] - Starting iteration 515. [2026-03-26 02:43:49,434][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:43:49,435][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:43:53,176][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:43:56,808][__main__][INFO] - Number of regex retries in iteration 515: 1 [2026-03-26 02:43:56,809][__main__][INFO] - agents played in iteration 515 are Bob, Alice [2026-03-26 02:43:57,726][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:43:58,317][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:43:58,776][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:43:59,282][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:43:59,784][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:44:00,285][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:44:00,786][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:44:01,287][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:44:01,788][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:44:02,289][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:44:02,790][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:44:03,291][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:44:03,792][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:44:04,292][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:44:04,795][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:44:05,297][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:44:05,798][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:44:06,300][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:44:06,800][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:44:07,303][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:44:07,805][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:44:08,308][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:44:08,808][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:44:09,309][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:44:09,809][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:44:10,309][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:44:10,808][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:44:11,311][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:44:11,812][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:44:12,312][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:44:12,811][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:44:13,311][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:44:13,811][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:44:14,312][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:44:14,815][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:44:15,317][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:44:15,818][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:44:16,320][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:44:16,822][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:44:17,323][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:44:17,824][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:44:18,326][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:44:18,828][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:44:19,329][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:44:19,830][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:44:20,331][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:44:20,833][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:44:21,335][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:44:21,837][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:44:22,338][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:44:22,843][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:44:23,345][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:44:23,847][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:44:24,350][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:44:24,852][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:44:25,354][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:44:25,856][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:44:26,359][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:44:26,860][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:44:27,364][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:44:27,866][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:44:28,367][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:44:28,869][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:44:29,371][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:44:29,873][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:44:30,374][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:44:30,875][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:44:31,376][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:44:31,876][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:44:32,378][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:44:32,879][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:44:33,380][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:44:33,881][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:44:34,382][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:44:34,883][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:44:35,384][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:44:35,885][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:44:36,386][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:44:36,889][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:44:37,394][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:44:37,894][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:44:38,397][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:44:38,898][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:44:39,399][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:44:39,900][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:44:40,400][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:44:40,901][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:44:41,405][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:44:41,906][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:44:42,408][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:44:42,907][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:44:43,408][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:44:43,907][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:44:44,407][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:44:44,907][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:44:45,407][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:44:45,908][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:44:46,408][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:44:46,908][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:44:47,407][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:44:47,906][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:44:48,406][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:44:48,906][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:44:49,407][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:44:49,907][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:44:50,407][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:44:50,907][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:44:51,407][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:44:51,907][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:44:52,408][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:44:52,908][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:44:53,408][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:44:53,909][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:44:54,410][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:44:54,911][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:44:55,413][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:44:55,915][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:44:56,417][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:44:56,919][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:44:57,421][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:44:57,921][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:44:58,424][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:44:58,927][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:44:59,428][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:44:59,929][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:45:00,429][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:45:00,931][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:45:01,433][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:45:01,936][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:45:02,438][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 02:45:03,059][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-26 02:45:03,792][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:45:03,794][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:45:03,795][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:45:04,443][__main__][INFO] - Iteration 516 took 1m 15s (9.83% Gen, 89.30% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 51h 20m 37s. Estimated total time: 62h 30m 28s. Time estimates for 10 more iterations: 12m 30s, 100 more iterations: 2h 5m 0s, 500 more iterations: 10h 25m 4s. [2026-03-26 02:45:04,445][__main__][INFO] - Starting iteration 516. [2026-03-26 02:45:04,845][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:45:04,845][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:45:09,669][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:45:11,892][__main__][INFO] - Number of regex retries in iteration 516: 1 [2026-03-26 02:45:11,893][__main__][INFO] - agents played in iteration 516 are Bob, Alice [2026-03-26 02:45:12,807][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:45:13,393][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:45:13,851][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:45:14,356][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:45:14,857][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:45:15,359][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:45:15,860][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:45:16,361][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:45:16,862][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:45:17,363][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:45:17,867][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:45:18,369][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:45:18,870][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:45:19,372][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:45:19,874][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:45:20,376][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:45:20,879][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:45:21,382][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:45:21,884][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:45:22,385][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:45:22,887][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:45:23,388][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:45:23,890][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:45:24,393][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:45:24,896][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:45:25,398][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:45:25,899][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:45:26,400][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:45:26,901][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:45:27,402][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:45:27,903][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:45:28,404][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:45:28,906][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:45:29,407][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:45:29,908][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:45:30,412][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:45:30,914][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:45:31,415][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:45:31,915][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:45:32,417][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:45:32,920][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:45:33,421][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:45:33,924][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:45:34,426][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:45:34,928][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:45:35,429][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:45:35,931][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:45:36,434][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:45:36,937][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:45:37,439][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:45:37,941][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:45:38,444][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:45:38,946][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:45:39,448][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:45:39,950][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:45:40,452][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:45:40,954][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:45:41,458][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:45:41,962][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:45:42,466][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:45:42,968][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:45:43,470][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:45:43,973][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:45:44,475][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:45:44,978][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:45:45,482][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:45:45,983][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:45:46,484][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:45:46,985][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:45:47,486][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:45:47,987][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:45:48,488][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:45:48,989][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:45:49,490][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:45:49,991][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:45:50,493][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:45:50,995][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:45:51,497][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:45:51,998][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:45:52,501][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:45:53,002][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:45:53,504][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:45:54,006][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:45:54,507][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:45:55,008][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:45:55,509][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:45:56,009][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:45:56,510][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:45:57,011][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:45:57,512][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:45:58,013][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:45:58,514][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:45:59,014][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:45:59,516][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:46:00,019][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:46:00,520][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:46:01,021][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:46:01,522][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:46:02,023][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:46:02,524][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:46:03,024][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:46:03,526][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:46:04,027][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:46:04,528][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:46:05,028][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:46:05,528][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:46:06,029][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:46:06,529][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:46:07,034][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:46:07,537][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:46:08,039][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:46:08,541][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:46:09,045][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:46:09,547][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:46:10,052][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:46:10,555][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:46:11,056][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:46:11,559][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:46:12,062][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:46:12,563][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:46:13,064][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:46:13,566][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:46:14,068][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:46:14,570][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:46:15,072][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:46:15,574][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:46:16,077][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:46:16,579][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:46:17,081][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:46:17,584][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 02:46:18,215][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-26 02:46:18,952][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:46:18,954][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:46:18,955][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:46:19,602][__main__][INFO] - Iteration 517 took 1m 14s (9.43% Gen, 89.71% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 6m 46s. Estimated total time: 62h 17m 52s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 35s, 500 more iterations: 10h 22m 58s. [2026-03-26 02:46:19,604][__main__][INFO] - Starting iteration 517. [2026-03-26 02:46:20,004][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:46:20,004][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:46:22,351][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:46:23,610][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:46:24,877][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:46:27,327][__main__][INFO] - Number of regex retries in iteration 517: 3 [2026-03-26 02:46:27,328][__main__][INFO] - agents played in iteration 517 are Bob, Alice [2026-03-26 02:46:28,249][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:46:28,835][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:46:29,294][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:46:29,801][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:46:30,303][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:46:30,805][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:46:31,307][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:46:31,809][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:46:32,311][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:46:32,812][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:46:33,314][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:46:33,815][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:46:34,317][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:46:34,819][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:46:35,320][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:46:35,822][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:46:36,323][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:46:36,825][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:46:37,326][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:46:37,827][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:46:38,330][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:46:38,831][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:46:39,332][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:46:39,834][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:46:40,339][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:46:40,841][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:46:41,346][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:46:41,849][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:46:42,351][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:46:42,852][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:46:43,355][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:46:43,857][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:46:44,360][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:46:44,862][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:46:45,363][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:46:45,865][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:46:46,366][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:46:46,866][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:46:47,367][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:46:47,869][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:46:48,370][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:46:48,871][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:46:49,375][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:46:49,878][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:46:50,380][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:46:50,883][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:46:51,385][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:46:51,886][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:46:52,388][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:46:52,890][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:46:53,391][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:46:53,894][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:46:54,394][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:46:54,897][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:46:55,399][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:46:55,900][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:46:56,402][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:46:56,904][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:46:57,407][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:46:57,909][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:46:58,413][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:46:58,916][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:46:59,419][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:46:59,922][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:47:00,424][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:47:00,927][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:47:01,429][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:47:01,930][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:47:02,432][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:47:02,932][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:47:03,436][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:47:03,938][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:47:04,440][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:47:04,942][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:47:05,444][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:47:05,946][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:47:06,448][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:47:06,949][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:47:07,451][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:47:07,953][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:47:08,454][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:47:08,956][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:47:09,459][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:47:09,962][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:47:10,466][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:47:10,971][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:47:11,476][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:47:11,979][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:47:12,481][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:47:12,984][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:47:13,485][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:47:13,986][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:47:14,487][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:47:14,988][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:47:15,490][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:47:15,992][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:47:16,493][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:47:16,994][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:47:17,495][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:47:17,998][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:47:18,500][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:47:19,002][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:47:19,503][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:47:20,005][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:47:20,506][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:47:21,007][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:47:21,509][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:47:22,011][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:47:22,513][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:47:23,015][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:47:23,518][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:47:24,020][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:47:24,522][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:47:25,024][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:47:25,526][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:47:26,027][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:47:26,527][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:47:27,029][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:47:27,530][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:47:28,032][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:47:28,533][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:47:29,035][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:47:29,540][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:47:30,044][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:47:30,547][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:47:31,050][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:47:31,553][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:47:32,055][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:47:32,560][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:47:33,063][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21750 tokens. [2026-03-26 02:47:33,685][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-26 02:47:34,426][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:47:34,428][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:47:34,429][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:47:35,128][__main__][INFO] - Iteration 518 took 1m 15s (9.75% Gen, 89.32% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 23m 52s. Estimated total time: 62h 36m 14s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 12s, 500 more iterations: 10h 26m 2s. [2026-03-26 02:47:35,130][__main__][INFO] - Starting iteration 518. [2026-03-26 02:47:35,532][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:47:35,533][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:47:42,074][__main__][INFO] - Number of regex retries in iteration 518: 0 [2026-03-26 02:47:42,074][__main__][INFO] - agents played in iteration 518 are Bob, Alice [2026-03-26 02:47:42,993][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:47:43,569][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:47:44,029][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:47:44,537][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:47:45,040][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:47:45,543][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:47:46,045][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:47:46,548][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:47:47,050][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:47:47,552][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:47:48,054][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:47:48,556][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:47:49,057][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:47:49,559][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:47:50,060][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:47:50,561][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:47:51,062][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:47:51,564][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:47:52,066][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:47:52,568][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:47:53,070][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:47:53,572][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:47:54,075][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:47:54,577][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:47:55,079][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:47:55,581][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:47:56,083][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:47:56,585][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:47:57,086][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:47:57,587][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:47:58,088][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:47:58,589][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:47:59,089][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:47:59,590][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:48:00,092][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:48:00,594][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:48:01,097][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:48:01,599][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:48:02,101][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:48:02,603][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:48:03,105][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:48:03,607][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:48:04,107][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:48:04,605][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:48:05,105][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:48:05,605][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:48:06,105][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:48:06,605][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:48:07,104][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:48:07,604][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:48:08,103][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:48:08,603][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:48:09,103][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:48:09,604][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:48:10,104][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:48:10,604][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:48:11,106][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:48:11,605][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:48:12,107][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:48:12,608][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:48:13,108][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:48:13,609][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:48:14,110][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:48:14,611][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:48:15,112][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:48:15,613][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:48:16,116][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:48:16,618][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:48:17,121][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:48:17,623][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:48:18,125][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:48:18,628][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:48:19,131][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:48:19,633][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:48:20,134][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:48:20,637][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:48:21,138][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:48:21,640][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:48:22,141][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:48:22,642][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:48:23,144][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:48:23,646][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:48:24,150][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:48:24,653][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:48:25,156][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:48:25,659][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:48:26,162][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:48:26,664][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:48:27,167][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:48:27,671][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:48:28,172][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:48:28,673][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:48:29,173][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:48:29,674][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:48:30,178][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:48:30,679][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:48:31,181][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:48:31,682][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:48:32,184][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:48:32,686][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:48:33,188][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:48:33,689][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:48:34,193][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:48:34,696][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:48:35,199][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:48:35,701][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:48:36,203][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:48:36,705][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:48:37,206][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:48:37,706][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:48:38,206][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:48:38,706][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:48:39,207][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:48:39,707][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:48:40,207][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:48:40,708][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:48:41,209][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:48:41,709][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:48:42,209][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:48:42,709][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:48:43,210][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:48:43,710][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:48:44,211][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:48:44,712][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:48:45,213][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:48:45,714][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:48:46,216][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:48:46,717][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:48:47,218][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:48:47,720][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 02:48:48,329][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-26 02:48:49,065][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:48:49,068][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:48:49,069][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:48:49,713][__main__][INFO] - Iteration 519 took 1m 14s (8.82% Gen, 90.31% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 50h 35m 27s. Estimated total time: 61h 49m 4s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 38s, 500 more iterations: 10h 18m 10s. [2026-03-26 02:48:49,715][__main__][INFO] - Starting iteration 519. [2026-03-26 02:48:50,112][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:48:50,113][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:48:51,238][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:48:56,976][__main__][INFO] - Number of regex retries in iteration 519: 1 [2026-03-26 02:48:56,977][__main__][INFO] - agents played in iteration 519 are Bob, Alice [2026-03-26 02:48:57,899][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:48:58,477][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:48:58,934][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:48:59,441][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:48:59,944][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:49:00,446][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:49:00,947][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:49:01,448][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:49:01,949][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:49:02,450][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:49:02,951][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:49:03,452][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:49:03,952][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:49:04,450][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:49:04,953][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:49:05,454][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:49:05,955][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:49:06,456][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:49:06,959][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:49:07,462][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:49:07,964][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:49:08,465][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:49:08,967][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:49:09,466][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:49:09,966][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:49:10,467][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:49:10,971][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:49:11,476][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:49:11,979][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:49:12,483][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:49:12,987][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:49:13,489][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:49:13,990][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:49:14,491][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:49:14,994][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:49:15,497][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:49:15,999][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:49:16,501][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:49:17,003][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:49:17,506][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:49:18,007][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:49:18,510][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:49:19,012][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:49:19,515][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:49:20,018][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:49:20,520][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:49:21,021][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:49:21,523][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:49:22,025][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:49:22,527][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:49:23,028][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:49:23,531][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:49:24,032][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:49:24,534][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:49:25,037][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:49:25,539][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:49:26,041][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:49:26,542][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:49:27,065][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:49:27,568][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:49:28,070][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:49:28,573][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:49:29,076][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:49:29,579][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:49:30,082][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:49:30,586][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:49:31,087][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:49:31,587][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:49:32,088][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:49:32,588][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:49:33,088][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:49:33,588][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:49:34,088][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:49:34,588][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:49:35,089][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:49:35,589][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:49:36,089][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:49:36,590][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:49:37,089][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:49:37,589][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:49:38,089][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:49:38,589][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:49:39,089][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:49:39,589][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:49:40,088][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:49:40,588][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:49:41,088][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:49:41,591][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:49:42,089][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:49:42,589][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:49:43,089][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:49:43,590][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:49:44,092][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:49:44,593][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:49:45,094][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:49:45,595][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:49:46,096][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:49:46,598][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:49:47,100][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:49:47,602][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:49:48,104][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:49:48,606][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:49:49,107][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:49:49,608][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:49:50,110][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:49:50,612][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:49:51,113][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:49:51,615][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:49:52,118][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:49:52,620][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:49:53,124][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:49:53,627][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:49:54,129][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:49:54,630][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:49:55,132][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:49:55,633][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:49:56,136][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:49:56,638][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:49:57,140][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:49:57,642][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:49:58,144][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:49:58,647][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:49:59,149][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:49:59,652][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:50:00,155][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:50:00,657][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:50:01,160][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:50:01,662][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:50:02,164][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:50:02,667][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21703 tokens. [2026-03-26 02:50:03,275][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-26 02:50:04,010][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:50:04,012][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:50:04,014][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:50:04,649][__main__][INFO] - Iteration 520 took 1m 14s (9.21% Gen, 89.94% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 50h 51m 59s. Estimated total time: 62h 6m 50s. Time estimates for 10 more iterations: 12m 25s, 100 more iterations: 2h 4m 13s, 500 more iterations: 10h 21m 8s. [2026-03-26 02:50:04,651][__main__][INFO] - Starting iteration 520. [2026-03-26 02:50:05,049][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:50:05,050][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:50:11,743][__main__][INFO] - Number of regex retries in iteration 520: 0 [2026-03-26 02:50:11,744][__main__][INFO] - agents played in iteration 520 are Bob, Alice [2026-03-26 02:50:12,679][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:50:13,258][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:50:13,717][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:50:14,226][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:50:14,729][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:50:15,231][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:50:15,733][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:50:16,235][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:50:16,738][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:50:17,239][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:50:17,741][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:50:18,243][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:50:18,745][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:50:19,248][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:50:19,749][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:50:20,251][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:50:20,752][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:50:21,254][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:50:21,756][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:50:22,258][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:50:22,758][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:50:23,259][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:50:23,760][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:50:24,262][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:50:24,764][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:50:25,265][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:50:25,767][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:50:26,267][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:50:26,767][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:50:27,267][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:50:27,767][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:50:28,268][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:50:28,769][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:50:29,270][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:50:29,773][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:50:30,275][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:50:30,779][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:50:31,281][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:50:31,783][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:50:32,286][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:50:32,787][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:50:33,289][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:50:33,790][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:50:34,291][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:50:34,792][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:50:35,293][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:50:35,793][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:50:36,294][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:50:36,798][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:50:37,303][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:50:37,803][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:50:38,303][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:50:38,803][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:50:39,303][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:50:39,802][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:50:40,301][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:50:40,801][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:50:41,303][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:50:41,806][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:50:42,307][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:50:42,808][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:50:43,309][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:50:43,809][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:50:44,310][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:50:44,811][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:50:45,312][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:50:45,813][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:50:46,316][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:50:46,818][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:50:47,319][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:50:47,820][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:50:48,322][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:50:48,823][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:50:49,325][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:50:49,826][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:50:50,328][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:50:50,829][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:50:51,330][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:50:51,831][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:50:52,333][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:50:52,837][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:50:53,338][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:50:53,839][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:50:54,340][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:50:54,841][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:50:55,342][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:50:55,844][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:50:56,345][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:50:56,846][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:50:57,348][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:50:57,848][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:50:58,349][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:50:58,851][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:50:59,352][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:50:59,853][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:51:00,354][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:51:00,855][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:51:01,356][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:51:01,860][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:51:02,362][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:51:02,865][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:51:03,367][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:51:03,870][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:51:04,373][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:51:04,876][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:51:05,379][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:51:05,880][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:51:06,381][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:51:06,882][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:51:07,383][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:51:07,885][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:51:08,387][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:51:08,888][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:51:09,389][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:51:09,887][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:51:10,386][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:51:10,885][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:51:11,386][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:51:11,886][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:51:12,385][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:51:12,885][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:51:13,384][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:51:13,886][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:51:14,390][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:51:14,893][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:51:15,396][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:51:15,899][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:51:16,401][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:51:16,903][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:51:17,405][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 02:51:18,016][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.28%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-26 02:51:18,757][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:51:18,759][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:51:18,760][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:51:19,382][__main__][INFO] - Iteration 521 took 1m 14s (9.00% Gen, 90.16% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 50h 40m 35s. Estimated total time: 61h 56m 41s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 53s, 500 more iterations: 10h 19m 26s. [2026-03-26 02:51:19,384][__main__][INFO] - Starting iteration 521. [2026-03-26 02:51:19,784][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:51:19,785][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:51:25,895][mllm.models.large_language_model_local][WARNING] - Response Proposal: 8 hats, 10 books, 12 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:51:27,585][__main__][INFO] - Number of regex retries in iteration 521: 1 [2026-03-26 02:51:27,586][__main__][INFO] - agents played in iteration 521 are Bob, Alice [2026-03-26 02:51:28,498][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:51:29,076][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:51:29,534][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:51:30,041][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:51:30,543][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:51:31,045][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:51:31,547][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:51:32,049][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:51:32,551][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:51:33,052][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:51:33,553][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:51:34,055][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:51:34,557][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:51:35,058][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:51:35,560][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:51:36,061][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:51:36,562][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:51:37,059][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:51:37,560][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:51:38,060][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:51:38,561][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:51:39,062][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:51:39,563][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:51:40,065][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:51:40,566][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:51:41,067][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:51:41,571][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:51:42,073][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:51:42,575][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:51:43,076][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:51:43,578][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:51:44,080][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:51:44,581][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:51:45,082][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:51:45,585][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:51:46,087][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:51:46,589][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:51:47,091][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:51:47,593][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:51:48,095][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:51:48,598][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:51:49,101][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:51:49,602][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:51:50,104][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:51:50,604][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:51:51,104][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:51:51,604][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:51:52,104][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:51:52,604][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:51:53,105][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:51:53,605][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:51:54,106][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:51:54,607][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:51:55,107][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:51:55,607][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:51:56,107][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:51:56,608][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:51:57,109][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:51:57,609][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:51:58,110][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:51:58,610][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:51:59,110][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:51:59,611][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:52:00,112][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:52:00,613][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:52:01,113][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:52:01,614][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:52:02,117][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:52:02,619][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:52:03,121][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:52:03,623][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:52:04,126][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:52:04,627][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:52:05,128][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:52:05,629][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:52:06,129][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:52:06,629][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:52:07,133][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:52:07,636][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:52:08,138][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:52:08,639][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:52:09,140][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:52:09,641][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:52:10,142][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:52:10,643][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:52:11,144][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:52:11,648][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:52:12,149][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:52:12,650][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:52:13,150][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:52:13,651][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:52:14,152][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:52:14,654][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:52:15,158][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:52:15,662][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:52:16,165][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:52:16,667][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:52:17,168][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:52:17,669][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:52:18,172][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:52:18,676][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:52:19,178][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:52:19,680][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:52:20,183][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:52:20,685][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:52:21,187][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:52:21,688][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:52:22,189][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:52:22,689][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:52:23,189][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:52:23,689][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:52:24,189][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:52:24,690][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:52:25,189][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:52:25,691][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:52:26,191][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:52:26,692][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:52:27,192][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:52:27,693][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:52:28,194][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:52:28,694][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:52:29,195][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:52:29,696][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:52:30,197][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:52:30,698][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:52:31,199][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:52:31,700][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:52:32,201][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:52:32,703][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:52:33,204][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21699 tokens. [2026-03-26 02:52:33,814][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.34%, ΔTime: 00:01:04 [2026-03-26 02:52:34,547][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:52:34,549][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:52:34,551][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:52:35,212][__main__][INFO] - Iteration 522 took 1m 15s (10.34% Gen, 88.78% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 51h 34m 3s. Estimated total time: 62h 51m 25s. Time estimates for 10 more iterations: 12m 34s, 100 more iterations: 2h 5m 42s, 500 more iterations: 10h 28m 34s. [2026-03-26 02:52:35,214][__main__][INFO] - Starting iteration 522. [2026-03-26 02:52:35,614][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:52:35,615][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:52:38,466][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:52:42,452][__main__][INFO] - Number of regex retries in iteration 522: 1 [2026-03-26 02:52:42,453][__main__][INFO] - agents played in iteration 522 are Bob, Alice [2026-03-26 02:52:43,370][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:52:44,218][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:52:44,673][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:52:45,179][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:52:45,681][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:52:46,181][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:52:46,682][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:52:47,181][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:52:47,681][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:52:48,182][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:52:48,685][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:52:49,187][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:52:49,688][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:52:50,190][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:52:50,691][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:52:51,192][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:52:51,693][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:52:52,195][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:52:52,699][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:52:53,201][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:52:53,703][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:52:54,204][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:52:54,706][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:52:55,207][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:52:55,708][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:52:56,210][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:52:56,710][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:52:57,211][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:52:57,712][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:52:58,214][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:52:58,715][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:52:59,215][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:52:59,717][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:53:00,218][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:53:00,721][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:53:01,222][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:53:01,723][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:53:02,225][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:53:02,726][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:53:03,226][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:53:03,727][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:53:04,229][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:53:04,729][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:53:05,230][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:53:05,731][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:53:06,233][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:53:06,735][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:53:07,238][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:53:07,739][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:53:08,241][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:53:08,742][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:53:09,244][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:53:09,745][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:53:10,246][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:53:10,748][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:53:11,251][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:53:11,753][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:53:12,254][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:53:12,757][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:53:13,259][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:53:13,763][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:53:14,264][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:53:14,765][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:53:15,266][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:53:15,769][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:53:16,270][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:53:16,771][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:53:17,273][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:53:17,775][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:53:18,275][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:53:18,777][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:53:19,278][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:53:19,779][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:53:20,279][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:53:20,779][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:53:21,281][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:53:21,782][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:53:22,284][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:53:22,784][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:53:23,286][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:53:23,786][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:53:24,287][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:53:24,787][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:53:25,288][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:53:25,790][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:53:26,292][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:53:26,793][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:53:27,295][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:53:27,796][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:53:28,300][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:53:28,801][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:53:29,303][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:53:29,805][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:53:30,306][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:53:30,806][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:53:31,308][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:53:31,808][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:53:32,310][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:53:32,811][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:53:33,312][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:53:33,812][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:53:34,313][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:53:34,816][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:53:35,318][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:53:35,819][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:53:36,321][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:53:36,823][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:53:37,328][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:53:37,830][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:53:38,332][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:53:38,833][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:53:39,335][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:53:39,838][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:53:40,340][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:53:40,842][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:53:41,345][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:53:41,849][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:53:42,350][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:53:42,850][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:53:43,351][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:53:43,853][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:53:44,354][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:53:44,855][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:53:45,355][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:53:45,856][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:53:46,358][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:53:46,859][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:53:47,360][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:53:47,861][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:53:48,362][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-26 02:53:48,990][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.52%, Block Peak % of device VRAM: 62.20%, ΔTime: 00:01:04 [2026-03-26 02:53:49,724][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:53:49,726][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:53:49,727][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:53:50,550][__main__][INFO] - Iteration 523 took 1m 14s (9.12% Gen, 89.78% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 51h 8m 12s. Estimated total time: 62h 26m 49s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 53s, 500 more iterations: 10h 24m 28s. [2026-03-26 02:53:50,552][__main__][INFO] - Starting iteration 523. [2026-03-26 02:53:50,954][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:53:50,954][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:53:57,694][__main__][INFO] - Number of regex retries in iteration 523: 0 [2026-03-26 02:53:57,695][__main__][INFO] - agents played in iteration 523 are Bob, Alice [2026-03-26 02:53:58,609][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:53:59,188][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:53:59,644][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:54:00,150][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:54:00,651][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:54:01,152][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:54:01,653][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:54:02,153][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:54:02,653][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:54:03,155][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:54:03,658][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:54:04,159][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:54:04,661][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:54:05,162][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:54:05,664][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:54:06,165][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:54:06,667][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:54:07,168][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:54:07,668][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:54:08,168][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:54:08,668][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:54:09,167][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:54:09,667][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:54:10,167][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:54:10,667][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:54:11,169][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:54:11,671][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:54:12,172][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:54:12,673][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:54:13,175][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:54:13,677][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:54:14,179][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:54:14,680][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:54:15,181][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:54:15,682][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:54:16,183][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:54:16,685][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:54:17,189][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:54:17,691][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:54:18,191][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:54:18,693][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:54:19,195][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:54:19,696][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:54:20,197][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:54:20,699][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:54:21,201][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:54:21,701][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:54:22,203][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:54:22,704][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:54:23,205][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:54:23,709][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:54:24,210][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:54:24,711][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:54:25,213][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:54:25,716][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:54:26,218][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:54:26,721][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:54:27,223][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:54:27,725][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:54:28,227][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:54:28,729][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:54:29,231][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:54:29,733][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:54:30,235][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:54:30,739][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:54:31,241][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:54:31,742][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:54:32,244][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:54:32,745][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:54:33,246][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:54:33,747][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:54:34,247][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:54:34,748][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:54:35,249][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:54:35,750][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:54:36,251][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:54:36,752][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:54:37,254][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:54:37,757][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:54:38,258][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:54:38,760][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:54:39,262][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:54:39,764][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:54:40,265][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:54:40,767][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:54:41,270][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:54:41,771][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:54:42,271][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:54:42,772][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:54:43,273][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:54:43,774][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:54:44,275][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:54:44,776][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:54:45,277][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:54:45,779][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:54:46,281][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:54:46,782][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:54:47,284][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:54:47,785][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:54:48,286][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:54:48,787][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:54:49,287][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:54:49,788][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:54:50,289][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:54:50,790][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:54:51,292][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:54:51,792][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:54:52,294][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:54:52,795][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:54:53,297][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:54:53,798][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:54:54,300][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:54:54,801][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:54:55,302][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:54:55,804][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:54:56,305][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:54:56,811][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:54:57,314][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:54:57,817][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:54:58,320][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:54:58,823][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:54:59,326][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:54:59,829][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:55:00,332][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:55:00,836][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:55:01,341][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:55:01,845][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:55:02,349][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:55:02,851][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:55:03,355][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 02:55:03,977][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.23%, ΔTime: 00:01:04 [2026-03-26 02:55:04,720][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:55:04,722][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:55:04,723][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:55:05,373][__main__][INFO] - Iteration 524 took 1m 14s (9.06% Gen, 90.07% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 50h 41m 8s. Estimated total time: 62h 1m 0s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 2s, 500 more iterations: 10h 20m 10s. [2026-03-26 02:55:05,375][__main__][INFO] - Starting iteration 524. [2026-03-26 02:55:05,774][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:55:05,775][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:55:08,867][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 books, 10 balls, 10 hats did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:55:11,824][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:55:12,871][__main__][INFO] - Number of regex retries in iteration 524: 2 [2026-03-26 02:55:12,872][__main__][INFO] - agents played in iteration 524 are Bob, Alice [2026-03-26 02:55:13,786][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:55:14,367][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:55:14,827][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:55:15,334][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:55:15,837][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:55:16,340][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:55:16,842][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:55:17,347][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:55:17,851][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:55:18,353][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:55:18,856][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:55:19,358][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:55:19,859][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:55:20,361][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:55:20,863][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:55:21,366][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:55:21,867][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:55:22,368][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:55:22,872][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:55:23,374][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:55:23,877][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:55:24,379][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:55:24,882][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:55:25,384][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:55:25,886][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:55:26,388][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:55:26,888][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:55:27,390][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:55:27,891][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:55:28,392][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:55:28,892][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:55:29,394][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:55:29,895][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:55:30,397][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:55:30,898][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:55:31,400][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:55:31,900][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:55:32,402][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:55:32,902][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:55:33,404][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:55:33,905][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:55:34,406][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:55:34,910][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:55:35,414][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:55:35,918][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:55:36,422][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:55:36,925][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:55:37,427][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:55:37,930][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:55:38,433][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:55:38,936][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:55:39,437][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:55:39,938][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:55:40,440][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:55:40,941][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:55:41,445][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:55:41,948][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:55:42,449][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:55:42,950][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:55:43,450][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:55:43,951][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:55:44,453][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:55:44,954][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:55:45,456][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:55:45,957][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:55:46,457][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:55:46,959][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:55:47,463][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:55:47,966][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:55:48,468][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:55:48,970][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:55:49,471][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:55:49,972][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:55:50,474][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:55:50,976][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:55:51,476][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:55:51,976][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:55:52,477][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:55:52,978][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:55:53,480][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:55:53,980][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:55:54,481][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:55:54,983][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:55:55,484][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:55:55,986][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:55:56,487][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:55:56,989][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:55:57,490][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:55:57,992][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:55:58,493][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:55:58,992][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:55:59,493][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:55:59,995][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:56:00,496][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:56:00,997][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:56:01,498][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:56:01,998][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:56:02,499][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:56:03,001][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:56:03,503][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:56:04,004][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:56:04,506][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:56:05,007][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:56:05,508][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:56:06,009][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:56:06,511][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:56:07,013][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:56:07,515][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:56:08,016][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:56:08,518][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:56:09,020][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:56:09,522][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:56:10,024][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:56:10,526][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:56:11,027][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:56:11,530][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:56:12,031][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:56:12,533][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:56:13,034][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:56:13,535][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:56:14,036][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:56:14,537][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:56:15,040][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:56:15,540][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:56:16,041][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:56:16,542][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:56:17,043][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:56:17,546][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:56:18,049][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:56:18,551][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 02:56:19,165][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 02:56:19,903][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:56:19,905][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:56:19,907][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:56:20,741][__main__][INFO] - Iteration 525 took 1m 14s (9.47% Gen, 89.42% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 7m 14s. Estimated total time: 62h 28m 21s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 56s, 500 more iterations: 10h 24m 43s. [2026-03-26 02:56:20,743][__main__][INFO] - Starting iteration 525. [2026-03-26 02:56:21,142][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:56:21,143][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:56:28,470][__main__][INFO] - Number of regex retries in iteration 525: 0 [2026-03-26 02:56:28,471][__main__][INFO] - agents played in iteration 525 are Bob, Alice [2026-03-26 02:56:29,378][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:56:29,957][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:56:30,412][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:56:30,918][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:56:31,418][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:56:31,918][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:56:32,418][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:56:32,918][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:56:33,416][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:56:33,916][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:56:34,420][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:56:34,921][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:56:35,423][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:56:35,924][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:56:36,426][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:56:36,929][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:56:37,432][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:56:37,935][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:56:38,437][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:56:38,938][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:56:39,439][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:56:39,941][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:56:40,441][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:56:40,943][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:56:41,446][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:56:41,947][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:56:42,451][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:56:42,953][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:56:43,457][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:56:43,959][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:56:44,462][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:56:44,965][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:56:45,466][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:56:45,968][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:56:46,470][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:56:46,970][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:56:47,473][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:56:47,974][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:56:48,477][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:56:48,984][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:56:49,492][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:56:50,000][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:56:50,505][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:56:51,006][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:56:51,508][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:56:52,010][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:56:52,512][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:56:53,013][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:56:53,514][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:56:54,017][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:56:54,519][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:56:55,025][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:56:55,526][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:56:56,028][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:56:56,529][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:56:57,031][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:56:57,533][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:56:58,036][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:56:58,539][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:56:59,041][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:56:59,543][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:57:00,045][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:57:00,547][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:57:01,049][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:57:01,551][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:57:02,052][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:57:02,551][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:57:03,050][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:57:03,549][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:57:04,048][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:57:04,549][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:57:05,048][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:57:05,548][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:57:06,047][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:57:06,548][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:57:07,051][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:57:07,552][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:57:08,053][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:57:08,554][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:57:09,055][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:57:09,556][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:57:10,059][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:57:10,560][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:57:11,062][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:57:11,565][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:57:12,066][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:57:12,566][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:57:13,066][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:57:13,566][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:57:14,067][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:57:14,569][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:57:15,071][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:57:15,572][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:57:16,073][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:57:16,576][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:57:17,079][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:57:17,580][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:57:18,085][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:57:18,589][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:57:19,092][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:57:19,594][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:57:20,096][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:57:20,597][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:57:21,098][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:57:21,600][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:57:22,102][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:57:22,604][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:57:23,105][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:57:23,607][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:57:24,108][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:57:24,608][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:57:25,109][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:57:25,610][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:57:26,112][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:57:26,613][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:57:27,114][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:57:27,615][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:57:28,119][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:57:28,622][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:57:29,124][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:57:29,626][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:57:30,127][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:57:30,628][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:57:31,129][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:57:31,631][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:57:32,132][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:57:32,633][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:57:33,135][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:57:33,637][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:57:34,140][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21741 tokens. [2026-03-26 02:57:34,758][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.25%, ΔTime: 00:01:04 [2026-03-26 02:57:35,494][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:57:35,497][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:57:35,498][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:57:36,150][__main__][INFO] - Iteration 526 took 1m 15s (9.77% Gen, 89.36% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 8m 2s. Estimated total time: 62h 30m 25s. Time estimates for 10 more iterations: 12m 30s, 100 more iterations: 2h 5m 0s, 500 more iterations: 10h 25m 4s. [2026-03-26 02:57:36,152][__main__][INFO] - Starting iteration 526. [2026-03-26 02:57:36,553][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:57:36,554][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:57:38,312][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 02:57:43,612][__main__][INFO] - Number of regex retries in iteration 526: 1 [2026-03-26 02:57:43,613][__main__][INFO] - agents played in iteration 526 are Bob, Alice [2026-03-26 02:57:44,518][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:57:45,106][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:57:45,563][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:57:46,070][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:57:46,569][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:57:47,071][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:57:47,572][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:57:48,073][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:57:48,575][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:57:49,076][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:57:49,580][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:57:50,082][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:57:50,585][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:57:51,087][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:57:51,589][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:57:52,090][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:57:52,593][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:57:53,094][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:57:53,599][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:57:54,100][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:57:54,602][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:57:55,104][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:57:55,606][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:57:56,107][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:57:56,609][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:57:57,111][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:57:57,616][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:57:58,119][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:57:58,622][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:57:59,124][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:57:59,627][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:58:00,129][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:58:00,631][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:58:01,133][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:58:01,634][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:58:02,137][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:58:02,639][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:58:03,142][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:58:03,644][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:58:04,146][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:58:04,648][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:58:05,150][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:58:05,651][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:58:06,152][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:58:06,652][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:58:07,153][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:58:07,655][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:58:08,157][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:58:08,658][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:58:09,159][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:58:09,661][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:58:10,162][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:58:10,664][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:58:11,167][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:58:11,670][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:58:12,172][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:58:12,674][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:58:13,174][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:58:13,674][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:58:14,176][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:58:14,677][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:58:15,179][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:58:15,679][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:58:16,179][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:58:16,680][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:58:17,181][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:58:17,682][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:58:18,183][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:58:18,686][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:58:19,189][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:58:19,692][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:58:20,193][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:58:20,694][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:58:21,196][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:58:21,698][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:58:22,201][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:58:22,702][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:58:23,204][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:58:23,706][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:58:24,208][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:58:24,710][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:58:25,212][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:58:25,713][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:58:26,216][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:58:26,719][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:58:27,221][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:58:27,722][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:58:28,224][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:58:28,726][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:58:29,228][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:58:29,730][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:58:30,232][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:58:30,734][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:58:31,236][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:58:31,739][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:58:32,241][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:58:32,744][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:58:33,246][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:58:33,747][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:58:34,249][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:58:34,750][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:58:35,252][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:58:35,754][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:58:36,256][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:58:36,757][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:58:37,258][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:58:37,759][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:58:38,260][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:58:38,761][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:58:39,262][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:58:39,762][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:58:40,262][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:58:40,763][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:58:41,267][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:58:41,769][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:58:42,270][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:58:42,772][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:58:43,273][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:58:43,774][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:58:44,277][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:58:44,779][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:58:45,280][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 02:58:45,780][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 02:58:46,280][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 02:58:46,780][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 02:58:47,280][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 02:58:47,780][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 02:58:48,280][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 02:58:48,782][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 02:58:49,282][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21740 tokens. [2026-03-26 02:58:49,908][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.15%, Current % of VRAM taken: 60.51%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-26 02:58:50,650][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 02:58:50,652][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 02:58:50,654][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 02:58:51,328][__main__][INFO] - Iteration 527 took 1m 14s (9.44% Gen, 89.66% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 50h 55m 8s. Estimated total time: 62h 18m 46s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 37s, 500 more iterations: 10h 23m 7s. [2026-03-26 02:58:51,330][__main__][INFO] - Starting iteration 527. [2026-03-26 02:58:51,731][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 02:58:51,732][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 02:58:57,857][__main__][INFO] - Number of regex retries in iteration 527: 0 [2026-03-26 02:58:57,858][__main__][INFO] - agents played in iteration 527 are Bob, Alice [2026-03-26 02:58:58,761][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 02:58:59,348][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 02:58:59,806][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 02:59:00,314][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 02:59:00,818][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 02:59:01,321][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 02:59:01,824][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 02:59:02,327][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 02:59:02,830][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 02:59:03,333][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 02:59:03,837][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 02:59:04,340][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 02:59:04,842][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 02:59:05,345][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 02:59:05,848][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 02:59:06,351][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 02:59:06,854][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 02:59:07,357][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 02:59:07,862][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 02:59:08,366][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 02:59:08,868][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 02:59:09,372][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 02:59:09,875][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 02:59:10,379][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 02:59:10,882][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 02:59:11,389][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 02:59:11,892][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 02:59:12,394][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 02:59:12,896][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 02:59:13,399][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 02:59:13,901][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 02:59:14,404][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 02:59:14,906][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 02:59:15,408][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 02:59:15,910][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 02:59:16,414][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 02:59:16,918][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 02:59:17,421][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 02:59:17,924][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 02:59:18,427][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 02:59:18,931][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 02:59:19,437][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 02:59:19,941][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 02:59:20,445][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 02:59:20,947][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 02:59:21,449][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 02:59:21,950][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 02:59:22,453][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 02:59:22,955][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 02:59:23,457][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 02:59:23,960][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 02:59:24,463][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 02:59:24,966][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 02:59:25,468][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 02:59:25,971][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 02:59:26,473][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 02:59:26,975][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 02:59:27,479][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 02:59:27,983][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 02:59:28,488][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 02:59:28,990][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 02:59:29,493][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 02:59:29,997][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 02:59:30,500][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 02:59:31,003][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 02:59:31,506][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 02:59:32,007][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 02:59:32,509][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 02:59:33,011][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 02:59:33,513][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 02:59:34,015][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 02:59:34,518][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 02:59:35,020][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 02:59:35,522][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 02:59:36,024][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 02:59:36,526][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 02:59:37,031][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 02:59:37,536][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 02:59:38,039][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 02:59:38,541][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 02:59:39,044][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 02:59:39,546][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 02:59:40,049][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 02:59:40,553][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 02:59:41,058][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 02:59:41,565][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 02:59:42,069][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 02:59:42,572][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 02:59:43,077][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 02:59:43,581][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 02:59:44,083][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 02:59:44,586][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 02:59:45,087][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 02:59:45,589][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 02:59:46,090][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 02:59:46,592][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 02:59:47,093][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 02:59:47,595][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 02:59:48,097][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 02:59:48,602][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 02:59:49,106][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 02:59:49,609][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 02:59:50,112][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 02:59:50,616][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 02:59:51,119][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 02:59:51,622][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 02:59:52,124][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 02:59:52,626][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 02:59:53,128][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 02:59:53,629][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 02:59:54,130][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 02:59:54,632][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 02:59:55,134][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 02:59:55,637][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 02:59:56,140][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 02:59:56,644][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 02:59:57,147][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 02:59:57,649][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 02:59:58,153][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 02:59:58,656][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 02:59:59,160][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 02:59:59,663][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:00:00,165][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:00:00,668][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:00:01,171][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:00:01,673][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:00:02,175][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:00:02,680][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:00:03,183][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:00:03,686][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21760 tokens. [2026-03-26 03:00:04,306][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 03:00:05,049][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:00:05,051][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:00:05,052][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:00:05,709][__main__][INFO] - Iteration 528 took 1m 13s (8.28% Gen, 90.83% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 50h 14m 2s. Estimated total time: 61h 38m 54s. Time estimates for 10 more iterations: 12m 19s, 100 more iterations: 2h 3m 17s, 500 more iterations: 10h 16m 29s. [2026-03-26 03:00:05,711][__main__][INFO] - Starting iteration 528. [2026-03-26 03:00:06,110][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:00:06,110][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:00:07,907][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:00:13,420][__main__][INFO] - Number of regex retries in iteration 528: 1 [2026-03-26 03:00:13,421][__main__][INFO] - agents played in iteration 528 are Bob, Alice [2026-03-26 03:00:14,332][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:00:14,909][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:00:15,366][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:00:15,871][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:00:16,372][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:00:16,873][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:00:17,372][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:00:17,873][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:00:18,374][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:00:18,875][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:00:19,379][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:00:19,882][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:00:20,385][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:00:20,886][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:00:21,386][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:00:21,888][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:00:22,388][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:00:22,889][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:00:23,390][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:00:23,889][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:00:24,389][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:00:24,890][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:00:25,389][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:00:25,890][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:00:26,389][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:00:26,889][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:00:27,389][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:00:27,890][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:00:28,390][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:00:28,891][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:00:29,392][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:00:29,892][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:00:30,393][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:00:30,893][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:00:31,393][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:00:31,893][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:00:32,393][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:00:32,894][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:00:33,393][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:00:33,893][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:00:34,393][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:00:34,893][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:00:35,397][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:00:35,900][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:00:36,402][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:00:36,903][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:00:37,405][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:00:37,907][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:00:38,408][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:00:38,910][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:00:39,409][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:00:39,907][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:00:40,407][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:00:40,907][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:00:41,409][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:00:41,908][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:00:42,408][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:00:42,908][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:00:43,408][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:00:43,908][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:00:44,409][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:00:44,911][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:00:45,411][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:00:45,912][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:00:46,413][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:00:46,917][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:00:47,418][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:00:47,919][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:00:48,419][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:00:48,920][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:00:49,421][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:00:49,922][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:00:50,424][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:00:50,926][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:00:51,428][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:00:51,929][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:00:52,429][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:00:52,930][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:00:53,431][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:00:53,932][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:00:54,433][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:00:54,933][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:00:55,433][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:00:55,934][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:00:56,436][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:00:56,939][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:00:57,440][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:00:57,942][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:00:58,444][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:00:58,946][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:00:59,448][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:00:59,949][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:01:00,452][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:01:00,955][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:01:01,457][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:01:01,959][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:01:02,461][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:01:02,963][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:01:03,466][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:01:03,969][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:01:04,470][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:01:04,971][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:01:05,472][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:01:05,975][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:01:06,479][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:01:06,982][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:01:07,487][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:01:07,989][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:01:08,491][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:01:08,993][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:01:09,495][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:01:09,998][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:01:10,500][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:01:11,003][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:01:11,506][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:01:12,007][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:01:12,508][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:01:13,009][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:01:13,509][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:01:14,011][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:01:14,510][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:01:15,012][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:01:15,513][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:01:16,016][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:01:16,519][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:01:17,022][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:01:17,525][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:01:18,027][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:01:18,530][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:01:19,034][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21744 tokens. [2026-03-26 03:01:19,659][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.61%, Block Peak % of device VRAM: 62.31%, ΔTime: 00:01:04 [2026-03-26 03:01:20,441][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:01:20,444][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:01:20,445][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:01:21,183][__main__][INFO] - Iteration 529 took 1m 15s (9.74% Gen, 89.28% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 7m 33s. Estimated total time: 62h 33m 41s. Time estimates for 10 more iterations: 12m 30s, 100 more iterations: 2h 5m 7s, 500 more iterations: 10h 25m 36s. [2026-03-26 03:01:21,185][__main__][INFO] - Starting iteration 529. [2026-03-26 03:01:21,585][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:01:21,586][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:01:22,172][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:01:29,822][__main__][INFO] - Number of regex retries in iteration 529: 1 [2026-03-26 03:01:29,823][__main__][INFO] - agents played in iteration 529 are Bob, Alice [2026-03-26 03:01:30,733][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:01:31,324][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:01:31,780][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:01:32,287][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:01:32,790][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:01:33,292][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:01:33,795][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:01:34,297][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:01:34,801][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:01:35,303][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:01:35,805][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:01:36,307][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:01:36,808][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:01:37,310][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:01:37,811][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:01:38,313][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:01:38,815][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:01:39,318][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:01:39,821][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:01:40,324][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:01:40,826][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:01:41,332][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:01:41,835][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:01:42,337][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:01:42,840][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:01:43,342][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:01:43,844][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:01:44,346][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:01:44,849][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:01:45,351][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:01:45,853][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:01:46,355][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:01:46,858][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:01:47,359][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:01:47,859][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:01:48,360][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:01:48,861][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:01:49,362][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:01:49,863][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:01:50,365][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:01:50,867][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:01:51,367][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:01:51,871][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:01:52,374][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:01:52,877][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:01:53,379][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:01:53,882][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:01:54,385][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:01:54,888][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:01:55,390][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:01:55,894][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:01:56,397][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:01:56,900][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:01:57,403][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:01:57,906][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:01:58,409][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:01:58,911][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:01:59,413][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:01:59,918][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:02:00,423][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:02:00,926][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:02:01,428][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:02:01,931][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:02:02,433][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:02:02,936][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:02:03,440][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:02:03,942][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:02:04,444][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:02:04,947][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:02:05,448][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:02:05,950][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:02:06,453][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:02:06,956][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:02:07,458][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:02:07,959][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:02:08,460][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:02:08,962][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:02:09,463][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:02:09,964][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:02:10,466][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:02:10,966][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:02:11,469][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:02:11,971][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:02:12,473][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:02:12,975][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:02:13,477][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:02:13,979][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:02:14,481][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:02:14,982][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:02:15,483][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:02:15,984][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:02:16,485][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:02:16,986][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:02:17,487][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:02:17,988][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:02:18,489][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:02:18,990][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:02:19,491][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:02:19,989][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:02:20,488][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:02:20,988][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:02:21,487][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:02:21,987][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:02:22,487][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:02:22,988][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:02:23,490][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:02:23,993][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:02:24,494][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:02:24,994][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:02:25,496][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:02:25,996][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:02:26,497][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:02:26,998][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:02:27,500][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:02:28,002][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:02:28,504][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:02:29,005][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:02:29,507][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:02:30,009][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:02:30,509][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:02:31,011][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:02:31,513][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:02:32,015][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:02:32,519][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:02:33,022][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:02:33,526][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:02:34,028][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:02:34,532][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:02:35,035][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:02:35,538][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-26 03:02:36,165][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-26 03:02:36,908][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:02:36,910][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:02:36,912][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:02:37,613][__main__][INFO] - Iteration 530 took 1m 16s (10.83% Gen, 88.24% Train). Generation: 8s, Training: 1m 7s. Estimated remaining time: 51h 54m 1s. Estimated total time: 63h 21m 26s. Time estimates for 10 more iterations: 12m 40s, 100 more iterations: 2h 6m 42s, 500 more iterations: 10h 33m 34s. [2026-03-26 03:02:37,615][__main__][INFO] - Starting iteration 530. [2026-03-26 03:02:38,016][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:02:38,017][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:02:40,868][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:02:44,039][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:02:45,056][__main__][INFO] - Number of regex retries in iteration 530: 2 [2026-03-26 03:02:45,057][__main__][INFO] - agents played in iteration 530 are Bob, Alice [2026-03-26 03:02:45,967][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:02:46,548][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:02:47,005][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:02:47,511][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:02:48,014][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:02:48,517][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:02:49,020][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:02:49,521][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:02:50,022][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:02:50,524][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:02:51,024][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:02:51,526][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:02:52,026][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:02:52,526][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:02:53,027][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:02:53,527][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:02:54,027][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:02:54,527][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:02:55,029][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:02:55,532][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:02:56,032][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:02:56,534][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:02:57,035][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:02:57,540][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:02:58,042][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:02:58,543][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:02:59,045][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:02:59,546][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:03:00,047][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:03:00,548][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:03:01,050][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:03:01,552][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:03:02,053][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:03:02,555][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:03:03,055][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:03:03,558][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:03:04,059][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:03:04,560][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:03:05,061][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:03:05,561][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:03:06,063][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:03:06,565][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:03:07,067][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:03:07,569][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:03:08,070][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:03:08,572][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:03:09,075][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:03:09,578][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:03:10,080][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:03:10,583][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:03:11,086][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:03:11,590][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:03:12,091][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:03:12,592][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:03:13,093][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:03:13,594][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:03:14,095][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:03:14,596][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:03:15,097][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:03:15,599][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:03:16,101][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:03:16,602][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:03:17,103][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:03:17,604][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:03:18,104][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:03:18,606][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:03:19,107][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:03:19,609][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:03:20,110][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:03:20,611][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:03:21,112][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:03:21,614][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:03:22,115][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:03:22,617][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:03:23,118][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:03:23,621][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:03:24,123][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:03:24,624][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:03:25,125][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:03:25,628][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:03:26,128][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:03:26,628][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:03:27,130][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:03:27,631][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:03:28,134][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:03:28,637][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:03:29,141][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:03:29,645][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:03:30,147][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:03:30,649][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:03:31,150][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:03:31,651][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:03:32,152][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:03:32,653][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:03:33,153][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:03:33,654][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:03:34,156][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:03:34,658][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:03:35,159][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:03:35,659][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:03:36,160][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:03:36,661][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:03:37,161][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:03:37,662][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:03:38,164][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:03:38,665][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:03:39,168][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:03:39,669][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:03:40,171][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:03:40,672][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:03:41,175][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:03:41,678][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:03:42,181][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:03:42,684][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:03:43,186][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:03:43,688][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:03:44,189][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:03:44,692][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:03:45,192][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:03:45,693][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:03:46,194][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:03:46,696][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:03:47,199][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:03:47,701][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:03:48,204][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:03:48,707][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:03:49,209][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:03:49,711][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:03:50,212][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:03:50,712][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-26 03:03:51,330][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-26 03:03:52,067][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:03:52,070][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:03:52,071][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:03:52,720][__main__][INFO] - Iteration 531 took 1m 14s (9.42% Gen, 89.71% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 50h 46m 33s. Estimated total time: 62h 15m 13s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 30s, 500 more iterations: 10h 22m 32s. [2026-03-26 03:03:52,722][__main__][INFO] - Starting iteration 531. [2026-03-26 03:03:53,121][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:03:53,121][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:03:57,816][mllm.models.large_language_model_local][WARNING] - Response Given that my per-item values for hats and books are higher and Bob values balls more, my optimal strategy would be to propose to keep as many high-value items for myself. Here's my proposal: Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:04:00,290][__main__][INFO] - Number of regex retries in iteration 531: 1 [2026-03-26 03:04:00,291][__main__][INFO] - agents played in iteration 531 are Bob, Alice [2026-03-26 03:04:01,201][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:04:01,782][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:04:02,241][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:04:02,747][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:04:03,248][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:04:03,750][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:04:04,251][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:04:04,754][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:04:05,257][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:04:05,758][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:04:06,263][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:04:06,766][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:04:07,273][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:04:07,778][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:04:08,281][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:04:08,784][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:04:09,288][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:04:09,791][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:04:10,318][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:04:10,824][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:04:11,329][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:04:11,832][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:04:12,335][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:04:12,838][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:04:13,341][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:04:13,843][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:04:14,347][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:04:14,848][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:04:15,352][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:04:15,854][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:04:16,358][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:04:16,860][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:04:17,363][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:04:17,865][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:04:18,367][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:04:18,869][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:04:19,370][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:04:19,871][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:04:20,373][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:04:20,874][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:04:21,376][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:04:21,876][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:04:22,379][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:04:22,880][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:04:23,382][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:04:23,883][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:04:24,387][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:04:24,889][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:04:25,392][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:04:25,894][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:04:26,397][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:04:26,901][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:04:27,405][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:04:27,908][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:04:28,411][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:04:28,915][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:04:29,418][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:04:29,922][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:04:30,425][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:04:30,927][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:04:31,430][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:04:31,932][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:04:32,434][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:04:32,936][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:04:33,441][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:04:33,943][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:04:34,446][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:04:34,949][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:04:35,451][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:04:35,953][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:04:36,457][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:04:36,960][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:04:37,463][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:04:37,965][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:04:38,468][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:04:38,972][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:04:39,475][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:04:39,978][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:04:40,482][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:04:40,985][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:04:41,491][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:04:41,995][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:04:42,497][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:04:42,999][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:04:43,501][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:04:44,003][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:04:44,505][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:04:45,007][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:04:45,509][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:04:46,011][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:04:46,513][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:04:47,017][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:04:47,520][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:04:48,023][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:04:48,526][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:04:49,028][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:04:49,530][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:04:50,033][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:04:50,535][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:04:51,038][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:04:51,539][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:04:52,041][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:04:52,542][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:04:53,043][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:04:53,544][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:04:54,045][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:04:54,547][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:04:55,048][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:04:55,549][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:04:56,050][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:04:56,552][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:04:57,054][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:04:57,556][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:04:58,057][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:04:58,560][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:04:59,063][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:04:59,566][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:05:00,068][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:05:00,571][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:05:01,074][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:05:01,579][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:05:02,081][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:05:02,584][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:05:03,086][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:05:03,588][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:05:04,090][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:05:04,591][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:05:05,093][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:05:05,595][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:05:06,097][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 03:05:06,719][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 03:05:07,467][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:05:07,469][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:05:07,470][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:05:08,206][__main__][INFO] - Iteration 532 took 1m 15s (9.55% Gen, 89.47% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 4m 24s. Estimated total time: 62h 34m 19s. Time estimates for 10 more iterations: 12m 30s, 100 more iterations: 2h 5m 8s, 500 more iterations: 10h 25m 43s. [2026-03-26 03:05:08,210][__main__][INFO] - Starting iteration 532. [2026-03-26 03:05:08,613][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:05:08,614][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:05:12,379][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:05:15,894][__main__][INFO] - Number of regex retries in iteration 532: 1 [2026-03-26 03:05:15,895][__main__][INFO] - agents played in iteration 532 are Bob, Alice [2026-03-26 03:05:16,798][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:05:17,377][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:05:17,836][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:05:18,343][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:05:18,846][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:05:19,348][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:05:19,851][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:05:20,353][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:05:20,856][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:05:21,359][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:05:21,860][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:05:22,362][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:05:22,862][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:05:23,363][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:05:23,864][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:05:24,366][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:05:24,867][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:05:25,370][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:05:25,871][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:05:26,373][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:05:26,874][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:05:27,376][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:05:27,877][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:05:28,378][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:05:28,881][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:05:29,383][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:05:29,884][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:05:30,384][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:05:30,885][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:05:31,385][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:05:31,886][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:05:32,387][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:05:32,887][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:05:33,387][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:05:33,888][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:05:34,390][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:05:34,890][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:05:35,392][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:05:35,893][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:05:36,395][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:05:36,898][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:05:37,402][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:05:37,904][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:05:38,406][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:05:38,908][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:05:39,409][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:05:39,911][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:05:40,411][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:05:40,912][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:05:41,417][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:05:41,922][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:05:42,426][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:05:42,928][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:05:43,431][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:05:43,934][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:05:44,439][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:05:44,942][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:05:45,445][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:05:45,951][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:05:46,458][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:05:46,963][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:05:47,469][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:05:47,973][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:05:48,479][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:05:48,983][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:05:49,488][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:05:49,989][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:05:50,491][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:05:50,994][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:05:51,498][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:05:52,000][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:05:52,503][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:05:53,005][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:05:53,507][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:05:54,008][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:05:54,508][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:05:55,009][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:05:55,509][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:05:56,009][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:05:56,509][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:05:57,009][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:05:57,510][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:05:58,011][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:05:58,512][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:05:59,013][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:05:59,514][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:06:00,015][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:06:00,518][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:06:01,020][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:06:01,521][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:06:02,021][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:06:02,523][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:06:03,024][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:06:03,525][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:06:04,027][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:06:04,528][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:06:05,029][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:06:05,530][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:06:06,030][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:06:06,531][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:06:07,033][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:06:07,535][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:06:08,038][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:06:08,540][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:06:09,042][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:06:09,544][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:06:10,046][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:06:10,549][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:06:11,050][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:06:11,554][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:06:12,054][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:06:12,557][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:06:13,059][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:06:13,561][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:06:14,064][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:06:14,567][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:06:15,069][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:06:15,572][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:06:16,075][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:06:16,578][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:06:17,080][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:06:17,584][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:06:18,089][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:06:18,594][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:06:19,098][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:06:19,603][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:06:20,107][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:06:20,611][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:06:21,116][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:06:21,620][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21754 tokens. [2026-03-26 03:06:22,237][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.32%, Current % of VRAM taken: 60.68%, Block Peak % of device VRAM: 62.53%, ΔTime: 00:01:04 [2026-03-26 03:06:22,978][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:06:22,980][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:06:22,981][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:06:23,764][__main__][INFO] - Iteration 533 took 1m 15s (9.69% Gen, 89.27% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 6m 32s. Estimated total time: 62h 37m 42s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 15s, 500 more iterations: 10h 26m 17s. [2026-03-26 03:06:23,766][__main__][INFO] - Starting iteration 533. [2026-03-26 03:06:24,166][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:06:24,167][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:06:25,268][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:06:32,993][__main__][INFO] - Number of regex retries in iteration 533: 1 [2026-03-26 03:06:32,993][__main__][INFO] - agents played in iteration 533 are Bob, Alice [2026-03-26 03:06:33,902][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:06:34,486][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:06:34,939][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:06:35,444][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:06:35,944][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:06:36,444][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:06:36,943][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:06:37,443][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:06:37,943][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:06:38,444][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:06:38,947][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:06:39,448][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:06:39,949][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:06:40,450][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:06:40,951][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:06:41,453][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:06:41,955][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:06:42,457][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:06:42,959][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:06:43,461][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:06:43,962][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:06:44,464][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:06:44,965][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:06:45,467][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:06:45,969][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:06:46,470][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:06:46,972][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:06:47,473][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:06:47,974][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:06:48,476][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:06:48,979][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:06:49,481][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:06:49,982][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:06:50,484][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:06:50,985][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:06:51,487][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:06:51,988][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:06:52,489][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:06:52,991][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:06:53,493][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:06:53,995][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:06:54,498][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:06:55,002][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:06:55,505][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:06:56,007][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:06:56,508][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:06:57,010][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:06:57,513][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:06:58,016][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:06:58,518][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:06:59,020][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:06:59,520][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:07:00,022][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:07:00,524][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:07:01,025][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:07:01,526][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:07:02,026][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:07:02,527][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:07:03,029][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:07:03,530][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:07:04,032][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:07:04,533][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:07:05,034][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:07:05,537][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:07:06,039][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:07:06,541][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:07:07,044][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:07:07,545][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:07:08,046][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:07:08,546][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:07:09,046][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:07:09,547][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:07:10,046][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:07:10,546][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:07:11,049][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:07:11,552][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:07:12,054][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:07:12,557][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:07:13,059][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:07:13,561][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:07:14,062][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:07:14,563][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:07:15,065][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:07:15,567][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:07:16,069][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:07:16,571][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:07:17,072][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:07:17,573][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:07:18,074][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:07:18,579][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:07:19,081][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:07:19,583][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:07:20,084][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:07:20,585][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:07:21,087][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:07:21,589][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:07:22,091][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:07:22,593][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:07:23,094][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:07:23,595][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:07:24,099][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:07:24,601][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:07:25,103][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:07:25,604][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:07:26,105][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:07:26,606][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:07:27,111][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:07:27,616][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:07:28,120][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:07:28,623][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:07:29,126][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:07:29,629][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:07:30,131][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:07:30,634][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:07:31,135][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:07:31,635][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:07:32,135][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:07:32,637][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:07:33,138][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:07:33,640][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:07:34,140][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:07:34,641][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:07:35,143][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:07:35,645][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:07:36,148][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:07:36,650][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:07:37,152][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:07:37,653][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:07:38,155][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:07:38,658][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 03:07:39,279][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.19%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.25%, ΔTime: 00:01:04 [2026-03-26 03:07:40,018][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:07:40,019][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:07:40,021][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:07:40,735][__main__][INFO] - Iteration 534 took 1m 16s (11.53% Gen, 87.54% Train). Generation: 8s, Training: 1m 7s. Estimated remaining time: 52h 15m 59s. Estimated total time: 63h 48m 27s. Time estimates for 10 more iterations: 12m 45s, 100 more iterations: 2h 7m 36s, 500 more iterations: 10h 38m 4s. [2026-03-26 03:07:40,737][__main__][INFO] - Starting iteration 534. [2026-03-26 03:07:41,146][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:07:41,147][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:07:42,200][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 books, 10 balls, 10 hats did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:07:48,337][__main__][INFO] - Number of regex retries in iteration 534: 1 [2026-03-26 03:07:48,338][__main__][INFO] - agents played in iteration 534 are Bob, Alice [2026-03-26 03:07:49,248][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:07:49,835][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:07:50,292][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:07:50,797][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:07:51,299][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:07:51,800][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:07:52,301][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:07:52,803][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:07:53,304][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:07:53,805][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:07:54,307][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:07:54,807][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:07:55,307][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:07:55,807][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:07:56,308][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:07:56,808][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:07:57,308][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:07:57,809][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:07:58,314][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:07:58,823][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:07:59,327][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:07:59,829][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:08:00,332][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:08:00,835][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:08:01,341][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:08:01,844][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:08:02,346][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:08:02,847][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:08:03,349][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:08:03,850][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:08:04,351][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:08:04,853][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:08:05,354][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:08:05,856][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:08:06,357][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:08:06,859][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:08:07,361][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:08:07,863][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:08:08,365][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:08:08,867][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:08:09,369][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:08:09,871][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:08:10,373][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:08:10,876][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:08:11,380][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:08:11,883][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:08:12,385][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:08:12,887][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:08:13,388][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:08:13,889][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:08:14,391][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:08:14,894][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:08:15,395][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:08:15,898][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:08:16,400][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:08:16,902][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:08:17,404][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:08:17,906][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:08:18,408][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:08:18,911][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:08:19,413][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:08:19,915][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:08:20,417][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:08:20,920][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:08:21,423][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:08:21,925][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:08:22,427][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:08:22,928][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:08:23,429][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:08:23,928][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:08:24,429][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:08:24,930][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:08:25,430][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:08:25,931][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:08:26,432][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:08:26,933][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:08:27,434][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:08:27,940][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:08:28,442][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:08:28,943][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:08:29,448][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:08:29,949][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:08:30,451][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:08:30,954][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:08:31,458][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:08:31,961][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:08:32,463][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:08:32,966][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:08:33,469][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:08:33,971][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:08:34,473][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:08:34,974][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:08:35,475][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:08:35,976][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:08:36,476][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:08:36,981][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:08:37,484][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:08:37,986][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:08:38,487][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:08:38,988][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:08:39,489][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:08:39,990][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:08:40,492][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:08:40,993][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:08:41,497][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:08:41,998][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:08:42,502][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:08:43,004][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:08:43,505][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:08:44,007][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:08:44,508][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:08:45,009][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:08:45,510][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:08:46,012][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:08:46,514][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:08:47,014][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:08:47,516][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:08:48,017][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:08:48,522][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:08:49,024][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:08:49,526][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:08:50,028][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:08:50,529][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:08:51,031][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:08:51,533][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:08:52,035][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:08:52,539][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:08:53,042][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:08:53,544][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:08:54,046][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21751 tokens. [2026-03-26 03:08:54,668][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.26%, Current % of VRAM taken: 60.62%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 03:08:55,412][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:08:55,414][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:08:55,415][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:08:56,127][__main__][INFO] - Iteration 535 took 1m 14s (9.59% Gen, 89.46% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 50h 55m 21s. Estimated total time: 62h 29m 4s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 58s, 500 more iterations: 10h 24m 50s. [2026-03-26 03:08:56,131][__main__][INFO] - Starting iteration 535. [2026-03-26 03:08:56,531][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:08:56,531][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:08:58,650][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:08:59,807][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:09:03,119][__main__][INFO] - Number of regex retries in iteration 535: 2 [2026-03-26 03:09:03,119][__main__][INFO] - agents played in iteration 535 are Bob, Alice [2026-03-26 03:09:04,020][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:09:04,603][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:09:05,060][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:09:05,566][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:09:06,066][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:09:06,567][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:09:07,068][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:09:07,568][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:09:08,068][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:09:08,570][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:09:09,071][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:09:09,572][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:09:10,074][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:09:10,575][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:09:11,077][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:09:11,579][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:09:12,080][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:09:12,582][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:09:13,085][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:09:13,588][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:09:14,090][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:09:14,592][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:09:15,094][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:09:15,596][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:09:16,098][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:09:16,601][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:09:17,103][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:09:17,604][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:09:18,106][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:09:18,607][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:09:19,109][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:09:19,610][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:09:20,112][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:09:20,614][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:09:21,114][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:09:21,615][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:09:22,117][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:09:22,618][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:09:23,119][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:09:23,620][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:09:24,121][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:09:24,622][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:09:25,124][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:09:25,627][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:09:26,130][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:09:26,631][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:09:27,132][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:09:27,634][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:09:28,138][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:09:28,642][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:09:29,143][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:09:29,646][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:09:30,148][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:09:30,649][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:09:31,150][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:09:31,651][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:09:32,152][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:09:32,653][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:09:33,154][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:09:33,655][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:09:34,158][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:09:34,659][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:09:35,161][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:09:35,663][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:09:36,164][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:09:36,666][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:09:37,166][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:09:37,666][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:09:38,167][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:09:38,668][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:09:39,168][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:09:39,668][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:09:40,168][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:09:40,668][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:09:41,169][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:09:41,672][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:09:42,173][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:09:42,674][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:09:43,175][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:09:43,675][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:09:44,178][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:09:44,680][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:09:45,181][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:09:45,683][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:09:46,185][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:09:46,687][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:09:47,189][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:09:47,691][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:09:48,192][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:09:48,695][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:09:49,196][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:09:49,700][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:09:50,202][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:09:50,703][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:09:51,205][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:09:51,707][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:09:52,208][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:09:52,709][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:09:53,209][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:09:53,710][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:09:54,210][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:09:54,711][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:09:55,211][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:09:55,710][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:09:56,211][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:09:56,711][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:09:57,213][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:09:57,714][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:09:58,215][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:09:58,717][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:09:59,222][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:09:59,724][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:10:00,226][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:10:00,728][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:10:01,228][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:10:01,729][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:10:02,229][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:10:02,729][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:10:03,230][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:10:03,731][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:10:04,231][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:10:04,731][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:10:05,231][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:10:05,731][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:10:06,231][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:10:06,732][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:10:07,236][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:10:07,738][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:10:08,240][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:10:08,741][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 03:10:09,355][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.20%, ΔTime: 00:01:04 [2026-03-26 03:10:10,093][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:10:10,095][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:10:10,097][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:10:10,746][__main__][INFO] - Iteration 536 took 1m 14s (8.88% Gen, 90.25% Train). Generation: 6s, Training: 1m 6s. Estimated remaining time: 50h 15m 51s. Estimated total time: 61h 50m 48s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 41s, 500 more iterations: 10h 18m 28s. [2026-03-26 03:10:10,748][__main__][INFO] - Starting iteration 536. [2026-03-26 03:10:11,154][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:10:11,155][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:10:18,445][__main__][INFO] - Number of regex retries in iteration 536: 0 [2026-03-26 03:10:18,446][__main__][INFO] - agents played in iteration 536 are Bob, Alice [2026-03-26 03:10:19,349][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:10:19,938][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:10:20,394][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:10:20,899][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:10:21,400][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:10:21,901][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:10:22,402][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:10:22,903][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:10:23,404][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:10:23,905][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:10:24,407][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:10:24,909][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:10:25,410][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:10:25,912][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:10:26,414][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:10:26,915][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:10:27,417][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:10:27,920][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:10:28,421][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:10:28,923][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:10:29,425][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:10:29,926][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:10:30,427][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:10:30,930][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:10:31,432][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:10:31,935][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:10:32,436][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:10:32,938][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:10:33,440][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:10:33,940][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:10:34,441][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:10:34,942][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:10:35,443][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:10:35,944][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:10:36,445][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:10:36,946][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:10:37,447][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:10:37,948][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:10:38,449][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:10:38,950][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:10:39,451][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:10:39,951][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:10:40,452][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:10:40,953][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:10:41,456][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:10:41,958][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:10:42,458][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:10:42,959][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:10:43,461][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:10:43,962][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:10:44,462][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:10:44,962][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:10:45,461][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:10:45,962][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:10:46,463][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:10:46,964][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:10:47,463][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:10:47,963][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:10:48,463][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:10:48,964][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:10:49,465][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:10:49,966][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:10:50,467][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:10:50,968][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:10:51,467][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:10:51,967][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:10:52,469][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:10:52,969][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:10:53,470][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:10:53,971][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:10:54,471][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:10:54,972][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:10:55,472][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:10:55,971][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:10:56,472][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:10:56,974][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:10:57,475][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:10:57,977][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:10:58,478][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:10:58,981][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:10:59,482][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:10:59,985][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:11:00,487][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:11:00,988][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:11:01,488][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:11:01,988][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:11:02,488][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:11:02,987][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:11:03,487][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:11:03,987][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:11:04,488][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:11:04,987][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:11:05,488][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:11:05,988][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:11:06,488][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:11:06,988][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:11:07,489][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:11:07,988][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:11:08,490][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:11:08,991][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:11:09,492][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:11:09,994][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:11:10,495][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:11:10,997][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:11:11,500][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:11:12,002][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:11:12,504][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:11:13,006][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:11:13,508][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:11:14,008][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:11:14,509][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:11:15,010][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:11:15,510][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:11:16,010][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:11:16,510][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:11:17,010][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:11:17,509][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:11:18,010][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:11:18,510][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:11:19,009][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:11:19,508][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:11:20,008][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:11:20,508][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:11:21,007][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:11:21,507][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:11:22,007][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:11:22,505][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:11:23,005][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:11:23,505][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:11:24,005][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21752 tokens. [2026-03-26 03:11:24,625][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.15%, Current % of VRAM taken: 60.51%, Block Peak % of device VRAM: 62.30%, ΔTime: 00:01:04 [2026-03-26 03:11:25,359][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:11:25,361][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:11:25,362][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:11:26,012][__main__][INFO] - Iteration 537 took 1m 14s (9.74% Gen, 89.39% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 50h 46m 41s. Estimated total time: 62h 22m 54s. Time estimates for 10 more iterations: 12m 28s, 100 more iterations: 2h 4m 45s, 500 more iterations: 10h 23m 49s. [2026-03-26 03:11:26,014][__main__][INFO] - Starting iteration 537. [2026-03-26 03:11:26,413][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:11:26,413][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:11:35,338][__main__][INFO] - Number of regex retries in iteration 537: 0 [2026-03-26 03:11:35,339][__main__][INFO] - agents played in iteration 537 are Bob, Alice [2026-03-26 03:11:36,252][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:11:36,843][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:11:37,303][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:11:37,808][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:11:38,310][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:11:38,810][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:11:39,310][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:11:39,812][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:11:40,313][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:11:40,815][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:11:41,320][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:11:41,824][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:11:42,326][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:11:42,827][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:11:43,330][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:11:43,831][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:11:44,334][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:11:44,836][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:11:45,341][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:11:45,844][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:11:46,346][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:11:46,848][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:11:47,350][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:11:47,853][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:11:48,356][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:11:48,860][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:11:49,362][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:11:49,863][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:11:50,366][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:11:50,868][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:11:51,369][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:11:51,872][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:11:52,373][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:11:52,875][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:11:53,376][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:11:53,879][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:11:54,381][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:11:54,883][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:11:55,386][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:11:55,888][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:11:56,389][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:11:56,891][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:11:57,393][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:11:57,895][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:11:58,397][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:11:58,900][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:11:59,402][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:11:59,904][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:12:00,406][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:12:00,908][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:12:01,429][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:12:01,936][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:12:02,439][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:12:02,942][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:12:03,445][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:12:03,947][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:12:04,451][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:12:04,954][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:12:05,456][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:12:05,958][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:12:06,459][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:12:06,960][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:12:07,462][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:12:07,964][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:12:08,466][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:12:08,968][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:12:09,469][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:12:09,971][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:12:10,471][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:12:10,972][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:12:11,475][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:12:11,977][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:12:12,478][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:12:12,979][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:12:13,482][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:12:13,984][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:12:14,485][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:12:14,986][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:12:15,487][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:12:15,988][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:12:16,488][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:12:16,989][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:12:17,493][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:12:17,995][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:12:18,498][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:12:19,001][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:12:19,503][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:12:20,005][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:12:20,507][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:12:21,010][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:12:21,511][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:12:22,011][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:12:22,513][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:12:23,015][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:12:23,517][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:12:24,020][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:12:24,524][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:12:25,026][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:12:25,528][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:12:26,030][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:12:26,532][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:12:27,035][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:12:27,540][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:12:28,042][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:12:28,544][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:12:29,047][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:12:29,550][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:12:30,051][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:12:30,553][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:12:31,056][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:12:31,558][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:12:32,061][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:12:32,565][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:12:33,069][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:12:33,572][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:12:34,076][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:12:34,578][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:12:35,080][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:12:35,583][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:12:36,086][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:12:36,590][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:12:37,094][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:12:37,594][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:12:38,096][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:12:38,597][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:12:39,100][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:12:39,601][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:12:40,103][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:12:40,604][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:12:41,106][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21733 tokens. [2026-03-26 03:12:41,723][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 03:12:42,466][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:12:42,468][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:12:42,469][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:12:43,104][__main__][INFO] - Iteration 538 took 1m 16s (11.64% Gen, 87.53% Train). Generation: 8s, Training: 1m 7s. Estimated remaining time: 52h 17m 6s. Estimated total time: 63h 54m 35s. Time estimates for 10 more iterations: 12m 46s, 100 more iterations: 2h 7m 49s, 500 more iterations: 10h 39m 5s. [2026-03-26 03:12:43,106][__main__][INFO] - Starting iteration 538. [2026-03-26 03:12:43,505][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:12:43,506][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:12:44,087][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:12:44,091][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:12:44,567][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:12:46,400][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:12:50,805][__main__][INFO] - Number of regex retries in iteration 538: 4 [2026-03-26 03:12:50,806][__main__][INFO] - agents played in iteration 538 are Bob, Alice [2026-03-26 03:12:51,714][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:12:52,298][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:12:52,756][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:12:53,262][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:12:53,764][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:12:54,265][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:12:54,766][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:12:55,267][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:12:55,768][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:12:56,269][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:12:56,773][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:12:57,276][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:12:57,778][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:12:58,281][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:12:58,783][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:12:59,286][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:12:59,788][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:13:00,290][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:13:00,790][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:13:01,290][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:13:01,790][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:13:02,291][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:13:02,792][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:13:03,293][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:13:03,793][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:13:04,294][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:13:04,796][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:13:05,299][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:13:05,800][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:13:06,303][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:13:06,805][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:13:07,310][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:13:07,812][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:13:08,315][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:13:08,814][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:13:09,314][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:13:09,813][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:13:10,313][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:13:10,814][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:13:11,315][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:13:11,816][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:13:12,316][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:13:12,819][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:13:13,322][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:13:13,824][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:13:14,326][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:13:14,827][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:13:15,330][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:13:15,831][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:13:16,334][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:13:16,838][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:13:17,341][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:13:17,844][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:13:18,346][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:13:18,849][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:13:19,352][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:13:19,853][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:13:20,356][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:13:20,857][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:13:21,358][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:13:21,858][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:13:22,360][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:13:22,862][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:13:23,363][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:13:23,864][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:13:24,365][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:13:24,866][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:13:25,369][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:13:25,869][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:13:26,370][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:13:26,872][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:13:27,373][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:13:27,874][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:13:28,377][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:13:28,881][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:13:29,384][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:13:29,887][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:13:30,390][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:13:30,891][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:13:31,394][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:13:31,896][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:13:32,399][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:13:32,901][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:13:33,401][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:13:33,902][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:13:34,404][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:13:34,905][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:13:35,406][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:13:35,907][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:13:36,408][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:13:36,909][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:13:37,410][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:13:37,912][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:13:38,414][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:13:38,915][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:13:39,417][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:13:39,919][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:13:40,422][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:13:40,922][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:13:41,425][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:13:41,926][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:13:42,427][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:13:42,927][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:13:43,428][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:13:43,930][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:13:44,432][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:13:44,932][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:13:45,433][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:13:45,933][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:13:46,435][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:13:46,938][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:13:47,439][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:13:47,941][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:13:48,443][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:13:48,946][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:13:49,448][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:13:49,949][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:13:50,452][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:13:50,954][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:13:51,456][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:13:51,957][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:13:52,461][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:13:52,962][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:13:53,463][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:13:53,964][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:13:54,466][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:13:54,966][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:13:55,467][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:13:55,968][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:13:56,468][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21746 tokens. [2026-03-26 03:13:57,091][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:04 [2026-03-26 03:13:57,827][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:13:57,829][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:13:57,830][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:13:58,477][__main__][INFO] - Iteration 539 took 1m 14s (9.74% Gen, 89.40% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 50h 49m 53s. Estimated total time: 62h 28m 39s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 57s, 500 more iterations: 10h 24m 46s. [2026-03-26 03:13:58,480][__main__][INFO] - Starting iteration 539. [2026-03-26 03:13:58,879][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:13:58,880][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:14:02,521][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:14:05,299][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 1 y book, 10 z balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:14:06,334][__main__][INFO] - Number of regex retries in iteration 539: 2 [2026-03-26 03:14:06,335][__main__][INFO] - agents played in iteration 539 are Bob, Alice [2026-03-26 03:14:07,245][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:14:07,834][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:14:08,292][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:14:08,798][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:14:09,300][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:14:09,803][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:14:10,304][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:14:10,806][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:14:11,309][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:14:11,816][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:14:12,318][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:14:12,821][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:14:13,324][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:14:13,827][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:14:14,329][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:14:14,832][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:14:15,340][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:14:15,843][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:14:16,345][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:14:16,848][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:14:17,350][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:14:17,852][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:14:18,355][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:14:18,859][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:14:19,364][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:14:19,868][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:14:20,372][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:14:20,876][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:14:21,381][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:14:21,886][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:14:22,393][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:14:22,897][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:14:23,404][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:14:23,908][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:14:24,412][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:14:24,916][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:14:25,420][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:14:25,924][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:14:26,427][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:14:26,936][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:14:27,440][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:14:27,944][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:14:28,446][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:14:28,950][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:14:29,453][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:14:29,955][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:14:30,460][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:14:30,963][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:14:31,465][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:14:31,967][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:14:32,470][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:14:32,972][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:14:33,473][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:14:33,975][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:14:34,478][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:14:34,980][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:14:35,484][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:14:35,987][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:14:36,492][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:14:36,997][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:14:37,502][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:14:38,006][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:14:38,509][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:14:39,012][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:14:39,516][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:14:40,019][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:14:40,523][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:14:41,025][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:14:41,531][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:14:42,032][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:14:42,535][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:14:43,036][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:14:43,538][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:14:44,041][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:14:44,545][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:14:45,047][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:14:45,550][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:14:46,052][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:14:46,554][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:14:47,056][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:14:47,560][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:14:48,062][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:14:48,565][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:14:49,067][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:14:49,568][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:14:50,070][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:14:50,571][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:14:51,073][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:14:51,574][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:14:52,076][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:14:52,578][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:14:53,082][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:14:53,585][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:14:54,087][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:14:54,590][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:14:55,092][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:14:55,595][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:14:56,099][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:14:56,601][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:14:57,103][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:14:57,606][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:14:58,107][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:14:58,609][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:14:59,111][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:14:59,613][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:15:00,114][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:15:00,615][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:15:01,116][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:15:01,618][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:15:02,120][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:15:02,621][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:15:03,122][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:15:03,623][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:15:04,125][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:15:04,626][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:15:05,129][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:15:05,631][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:15:06,129][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:15:06,627][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:15:07,129][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:15:07,630][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:15:08,131][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:15:08,633][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:15:09,136][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:15:09,639][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:15:10,143][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:15:10,646][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:15:11,150][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:15:11,654][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:15:12,157][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21693 tokens. [2026-03-26 03:15:12,783][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.32%, Current % of VRAM taken: 60.68%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:04 [2026-03-26 03:15:13,518][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:15:13,520][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:15:13,522][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:15:14,240][__main__][INFO] - Iteration 540 took 1m 15s (9.89% Gen, 89.15% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 8m 3s. Estimated total time: 62h 48m 4s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 36s, 500 more iterations: 10h 28m 0s. [2026-03-26 03:15:14,242][__main__][INFO] - Starting iteration 540. [2026-03-26 03:15:14,642][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:15:14,643][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:15:20,972][__main__][INFO] - Number of regex retries in iteration 540: 0 [2026-03-26 03:15:20,973][__main__][INFO] - agents played in iteration 540 are Bob, Alice [2026-03-26 03:15:21,883][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:15:22,464][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:15:22,920][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:15:23,426][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:15:23,926][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:15:24,426][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:15:24,926][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:15:25,427][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:15:25,928][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:15:26,428][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:15:26,929][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:15:27,429][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:15:27,929][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:15:28,430][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:15:28,932][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:15:29,434][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:15:29,934][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:15:30,434][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:15:30,937][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:15:31,440][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:15:31,941][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:15:32,443][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:15:32,945][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:15:33,446][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:15:33,947][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:15:34,449][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:15:34,950][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:15:35,451][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:15:35,952][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:15:36,452][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:15:36,953][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:15:37,455][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:15:37,956][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:15:38,458][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:15:38,961][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:15:39,464][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:15:39,966][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:15:40,469][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:15:40,972][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:15:41,477][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:15:41,979][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:15:42,482][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:15:42,984][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:15:43,485][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:15:43,987][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:15:44,489][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:15:44,989][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:15:45,490][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:15:45,990][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:15:46,494][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:15:46,995][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:15:47,496][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:15:47,996][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:15:48,497][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:15:48,996][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:15:49,498][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:15:49,999][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:15:50,499][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:15:51,001][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:15:51,504][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:15:52,005][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:15:52,507][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:15:53,008][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:15:53,510][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:15:54,011][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:15:54,513][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:15:55,013][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:15:55,515][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:15:56,017][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:15:56,518][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:15:57,020][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:15:57,522][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:15:58,023][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:15:58,525][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:15:59,026][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:15:59,527][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:16:00,028][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:16:00,528][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:16:01,028][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:16:01,530][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:16:02,031][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:16:02,532][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:16:03,034][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:16:03,535][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:16:04,035][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:16:04,537][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:16:05,041][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:16:05,543][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:16:06,044][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:16:06,546][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:16:07,050][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:16:07,552][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:16:08,054][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:16:08,555][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:16:09,056][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:16:09,557][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:16:10,057][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:16:10,558][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:16:11,061][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:16:11,565][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:16:12,068][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:16:12,571][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:16:13,074][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:16:13,575][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:16:14,080][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:16:14,589][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:16:15,091][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:16:15,592][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:16:16,092][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:16:16,594][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:16:17,095][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:16:17,596][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:16:18,096][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:16:18,604][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:16:19,105][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:16:19,606][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:16:20,107][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:16:20,609][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:16:21,110][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:16:21,610][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:16:22,118][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:16:22,622][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:16:23,126][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:16:23,630][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:16:24,134][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:16:24,638][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:16:25,143][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:16:25,647][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:16:26,156][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:16:26,660][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21756 tokens. [2026-03-26 03:16:27,290][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.28%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-26 03:16:28,025][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:16:28,027][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:16:28,029][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:16:28,746][__main__][INFO] - Iteration 541 took 1m 14s (8.54% Gen, 90.49% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 50h 3m 58s. Estimated total time: 61h 45m 13s. Time estimates for 10 more iterations: 12m 21s, 100 more iterations: 2h 3m 30s, 500 more iterations: 10h 17m 32s. [2026-03-26 03:16:28,748][__main__][INFO] - Starting iteration 541. [2026-03-26 03:16:29,148][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:16:29,149][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:16:36,635][__main__][INFO] - Number of regex retries in iteration 541: 0 [2026-03-26 03:16:36,635][__main__][INFO] - agents played in iteration 541 are Bob, Alice [2026-03-26 03:16:37,548][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:16:38,130][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:16:38,588][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:16:39,094][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:16:39,596][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:16:40,098][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:16:40,602][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:16:41,104][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:16:41,608][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:16:42,109][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:16:42,612][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:16:43,116][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:16:43,618][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:16:44,121][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:16:44,624][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:16:45,126][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:16:45,628][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:16:46,130][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:16:46,630][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:16:47,130][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:16:47,630][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:16:48,129][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:16:48,630][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:16:49,130][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:16:49,631][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:16:50,131][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:16:50,633][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:16:51,134][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:16:51,635][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:16:52,136][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:16:52,639][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:16:53,141][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:16:53,643][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:16:54,144][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:16:54,645][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:16:55,145][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:16:55,645][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:16:56,145][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:16:56,647][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:16:57,146][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:16:57,647][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:16:58,147][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:16:58,649][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:16:59,151][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:16:59,653][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:17:00,155][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:17:00,656][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:17:01,158][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:17:01,659][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:17:02,162][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:17:02,663][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:17:03,165][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:17:03,667][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:17:04,168][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:17:04,668][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:17:05,169][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:17:05,670][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:17:06,170][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:17:06,670][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:17:07,171][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:17:07,671][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:17:08,171][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:17:08,671][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:17:09,171][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:17:09,671][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:17:10,172][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:17:10,673][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:17:11,175][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:17:11,677][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:17:12,180][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:17:12,681][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:17:13,183][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:17:13,685][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:17:14,186][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:17:14,689][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:17:15,190][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:17:15,692][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:17:16,194][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:17:16,696][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:17:17,198][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:17:17,701][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:17:18,203][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:17:18,703][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:17:19,203][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:17:19,703][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:17:20,203][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:17:20,703][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:17:21,203][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:17:21,702][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:17:22,202][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:17:22,703][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:17:23,204][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:17:23,706][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:17:24,206][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:17:24,708][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:17:25,210][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:17:25,710][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:17:26,211][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:17:26,710][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:17:27,209][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:17:27,709][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:17:28,209][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:17:28,710][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:17:29,210][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:17:29,710][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:17:30,210][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:17:30,711][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:17:31,212][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:17:31,715][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:17:32,218][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:17:32,720][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:17:33,222][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:17:33,724][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:17:34,227][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:17:34,729][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:17:35,229][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:17:35,731][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:17:36,232][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:17:36,732][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:17:37,237][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:17:37,740][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:17:38,242][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:17:38,742][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:17:39,244][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:17:39,748][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:17:40,250][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:17:40,750][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:17:41,252][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:17:41,753][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:17:42,254][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21744 tokens. [2026-03-26 03:17:42,871][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.56%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-26 03:17:43,611][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:17:43,613][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:17:43,614][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:17:44,528][__main__][INFO] - Iteration 542 took 1m 15s (9.93% Gen, 88.85% Train). Generation: 7s, Training: 1m 6s. Estimated remaining time: 51h 6m 29s. Estimated total time: 62h 49m 0s. Time estimates for 10 more iterations: 12m 33s, 100 more iterations: 2h 5m 38s, 500 more iterations: 10h 28m 10s. [2026-03-26 03:17:44,530][__main__][INFO] - Starting iteration 542. [2026-03-26 03:17:44,928][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:17:44,929][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:17:51,489][__main__][INFO] - Number of regex retries in iteration 542: 0 [2026-03-26 03:17:51,490][__main__][INFO] - agents played in iteration 542 are Bob, Alice [2026-03-26 03:17:52,401][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:17:52,981][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:17:53,439][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:17:53,946][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:17:54,448][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:17:54,951][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:17:55,454][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:17:55,955][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:17:56,457][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:17:56,958][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:17:57,461][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:17:57,964][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:17:58,466][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:17:58,968][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:17:59,470][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:17:59,972][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:18:00,473][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:18:00,976][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:18:01,477][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:18:01,978][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:18:02,479][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:18:02,980][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:18:03,482][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:18:03,983][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:18:04,484][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:18:04,985][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:18:05,489][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:18:05,991][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:18:06,493][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:18:06,995][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:18:07,497][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:18:08,000][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:18:08,501][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:18:09,003][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:18:09,505][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:18:10,008][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:18:10,510][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:18:11,012][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:18:11,517][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:18:12,022][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:18:12,524][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:18:13,027][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:18:13,528][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:18:14,029][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:18:14,530][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:18:15,032][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:18:15,533][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:18:16,035][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:18:16,536][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:18:17,037][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:18:17,536][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:18:18,037][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:18:18,539][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:18:19,040][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:18:19,540][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:18:20,040][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:18:20,540][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:18:21,041][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:18:21,546][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:18:22,050][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:18:22,554][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:18:23,057][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:18:23,560][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:18:24,065][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:18:24,568][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:18:25,072][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:18:25,573][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:18:26,075][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:18:26,576][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:18:27,079][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:18:27,582][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:18:28,084][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:18:28,585][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:18:29,087][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:18:29,588][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:18:30,090][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:18:30,592][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:18:31,094][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:18:31,594][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:18:32,095][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:18:32,599][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:18:33,102][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:18:33,603][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:18:34,104][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:18:34,604][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:18:35,105][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:18:35,606][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:18:36,106][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:18:36,607][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:18:37,107][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:18:37,609][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:18:38,110][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:18:38,611][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:18:39,113][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:18:39,615][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:18:40,117][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:18:40,618][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:18:41,124][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:18:41,627][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:18:42,131][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:18:42,633][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:18:43,135][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:18:43,637][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:18:44,140][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:18:44,644][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:18:45,146][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:18:45,648][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:18:46,149][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:18:46,650][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:18:47,151][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:18:47,652][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:18:48,154][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:18:48,656][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:18:49,158][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:18:49,656][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:18:50,156][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:18:50,656][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:18:51,157][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:18:51,657][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:18:52,157][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:18:52,657][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:18:53,157][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:18:53,660][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:18:54,165][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:18:54,668][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:18:55,170][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:18:55,673][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:18:56,176][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:18:56,681][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:18:57,183][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 03:18:57,800][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.29%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.35%, ΔTime: 00:01:04 [2026-03-26 03:18:58,543][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:18:58,546][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:18:58,547][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:18:59,195][__main__][INFO] - Iteration 543 took 1m 14s (8.84% Gen, 90.29% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 50h 9m 37s. Estimated total time: 61h 53m 23s. Time estimates for 10 more iterations: 12m 22s, 100 more iterations: 2h 3m 46s, 500 more iterations: 10h 18m 53s. [2026-03-26 03:18:59,197][__main__][INFO] - Starting iteration 543. [2026-03-26 03:18:59,597][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:18:59,598][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:19:00,173][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:19:00,176][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:19:07,493][__main__][INFO] - Number of regex retries in iteration 543: 2 [2026-03-26 03:19:07,493][__main__][INFO] - agents played in iteration 543 are Bob, Alice [2026-03-26 03:19:08,407][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:19:08,991][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:19:09,449][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:19:09,955][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:19:10,458][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:19:10,961][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:19:11,466][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:19:11,969][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:19:12,471][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:19:12,973][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:19:13,475][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:19:13,979][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:19:14,482][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:19:14,984][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:19:15,486][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:19:15,989][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:19:16,491][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:19:16,993][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:19:17,497][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:19:18,000][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:19:18,504][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:19:19,007][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:19:19,509][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:19:20,011][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:19:20,513][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:19:21,017][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:19:21,515][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:19:22,014][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:19:22,513][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:19:23,013][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:19:23,512][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:19:24,012][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:19:24,511][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:19:25,010][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:19:25,513][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:19:26,015][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:19:26,518][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:19:27,020][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:19:27,523][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:19:28,025][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:19:28,528][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:19:29,030][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:19:29,533][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:19:30,035][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:19:30,536][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:19:31,040][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:19:31,542][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:19:32,045][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:19:32,547][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:19:33,049][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:19:33,548][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:19:34,048][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:19:34,548][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:19:35,049][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:19:35,548][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:19:36,048][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:19:36,548][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:19:37,048][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:19:37,550][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:19:38,051][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:19:38,552][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:19:39,054][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:19:39,555][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:19:40,057][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:19:40,558][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:19:41,061][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:19:41,566][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:19:42,070][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:19:42,571][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:19:43,072][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:19:43,574][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:19:44,076][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:19:44,579][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:19:45,080][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:19:45,582][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:19:46,085][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:19:46,587][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:19:47,089][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:19:47,593][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:19:48,095][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:19:48,597][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:19:49,099][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:19:49,603][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:19:50,105][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:19:50,607][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:19:51,108][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:19:51,610][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:19:52,112][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:19:52,615][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:19:53,120][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:19:53,619][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:19:54,118][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:19:54,617][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:19:55,116][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:19:55,615][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:19:56,113][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:19:56,612][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:19:57,112][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:19:57,615][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:19:58,117][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:19:58,620][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:19:59,124][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:19:59,626][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:20:00,128][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:20:00,632][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:20:01,136][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:20:01,642][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:20:02,145][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:20:02,648][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:20:03,151][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:20:03,653][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:20:04,160][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:20:04,665][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:20:05,169][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:20:05,669][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:20:06,170][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:20:06,671][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:20:07,172][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:20:07,673][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:20:08,178][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:20:08,679][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:20:09,181][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:20:09,685][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:20:10,189][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:20:10,692][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:20:11,196][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:20:11,701][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:20:12,208][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:20:12,712][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:20:13,215][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21708 tokens. [2026-03-26 03:20:13,838][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.23%, Current % of VRAM taken: 60.59%, Block Peak % of device VRAM: 62.36%, ΔTime: 00:01:04 [2026-03-26 03:20:14,575][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:20:14,577][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:20:14,578][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:20:15,254][__main__][INFO] - Iteration 544 took 1m 15s (10.44% Gen, 88.67% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 17m 51s. Estimated total time: 63h 2m 53s. Time estimates for 10 more iterations: 12m 36s, 100 more iterations: 2h 6m 5s, 500 more iterations: 10h 30m 28s. [2026-03-26 03:20:15,256][__main__][INFO] - Starting iteration 544. [2026-03-26 03:20:15,655][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:20:15,656][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:20:22,826][__main__][INFO] - Number of regex retries in iteration 544: 0 [2026-03-26 03:20:22,827][__main__][INFO] - agents played in iteration 544 are Bob, Alice [2026-03-26 03:20:23,738][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:20:24,323][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:20:24,779][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:20:25,286][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:20:25,787][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:20:26,289][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:20:26,790][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:20:27,294][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:20:27,799][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:20:28,302][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:20:28,808][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:20:29,314][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:20:29,818][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:20:30,322][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:20:30,824][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:20:31,328][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:20:31,831][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:20:32,334][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:20:32,835][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:20:33,338][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:20:33,842][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:20:34,344][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:20:34,846][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:20:35,348][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:20:35,849][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:20:36,351][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:20:36,855][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:20:37,362][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:20:37,866][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:20:38,370][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:20:38,877][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:20:39,381][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:20:39,886][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:20:40,389][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:20:40,898][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:20:41,406][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:20:41,912][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:20:42,418][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:20:42,924][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:20:43,429][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:20:43,932][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:20:44,437][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:20:44,938][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:20:45,440][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:20:45,942][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:20:46,442][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:20:46,944][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:20:47,445][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:20:47,946][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:20:48,446][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:20:48,948][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:20:49,449][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:20:49,951][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:20:50,452][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:20:50,953][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:20:51,454][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:20:51,955][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:20:52,464][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:20:52,972][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:20:53,479][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:20:53,989][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:20:54,497][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:20:55,002][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:20:55,507][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:20:56,011][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:20:56,516][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:20:57,022][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:20:57,527][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:20:58,031][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:20:58,534][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:20:59,038][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:20:59,543][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:21:00,048][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:21:00,551][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:21:01,055][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:21:01,562][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:21:02,066][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:21:02,571][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:21:03,075][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:21:03,579][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:21:04,085][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:21:04,589][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:21:05,091][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:21:05,595][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:21:06,096][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:21:06,600][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:21:07,103][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:21:07,605][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:21:08,107][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:21:08,609][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:21:09,111][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:21:09,614][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:21:10,117][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:21:10,620][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:21:11,124][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:21:11,630][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:21:12,133][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:21:12,636][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:21:13,140][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:21:13,643][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:21:14,147][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:21:14,651][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:21:15,155][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:21:15,659][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:21:16,162][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:21:16,666][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:21:17,168][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:21:17,670][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:21:18,173][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:21:18,675][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:21:19,176][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:21:19,677][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:21:20,179][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:21:20,682][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:21:21,184][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:21:21,685][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:21:22,187][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:21:22,688][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:21:23,190][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:21:23,691][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:21:24,192][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:21:24,693][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:21:25,195][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:21:25,696][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:21:26,200][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:21:26,702][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:21:27,204][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:21:27,706][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:21:28,209][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:21:28,711][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 03:21:29,331][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.20%, Current % of VRAM taken: 60.55%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:05 [2026-03-26 03:21:30,079][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:21:30,081][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:21:30,086][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:21:30,814][__main__][INFO] - Iteration 545 took 1m 15s (9.54% Gen, 89.49% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 50h 51m 41s. Estimated total time: 62h 37m 59s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 15s, 500 more iterations: 10h 26m 19s. [2026-03-26 03:21:30,816][__main__][INFO] - Starting iteration 545. [2026-03-26 03:21:31,215][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:21:31,216][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:21:31,815][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:21:37,634][__main__][INFO] - Number of regex retries in iteration 545: 1 [2026-03-26 03:21:37,635][__main__][INFO] - agents played in iteration 545 are Bob, Alice [2026-03-26 03:21:38,540][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:21:39,385][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:21:39,843][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:21:40,349][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:21:40,851][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:21:41,354][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:21:41,856][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:21:42,358][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:21:42,861][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:21:43,363][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:21:43,865][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:21:44,369][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:21:44,871][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:21:45,371][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:21:45,872][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:21:46,372][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:21:46,874][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:21:47,374][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:21:47,879][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:21:48,381][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:21:48,884][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:21:49,387][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:21:49,890][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:21:50,393][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:21:50,895][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:21:51,399][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:21:51,902][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:21:52,403][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:21:52,903][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:21:53,405][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:21:53,905][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:21:54,406][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:21:54,907][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:21:55,409][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:21:55,910][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:21:56,411][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:21:56,911][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:21:57,410][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:21:57,910][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:21:58,411][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:21:58,912][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:21:59,413][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:21:59,914][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:22:00,415][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:22:00,917][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:22:01,421][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:22:01,922][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:22:02,423][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:22:02,924][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:22:03,426][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:22:03,928][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:22:04,429][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:22:04,931][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:22:05,432][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:22:05,933][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:22:06,434][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:22:06,936][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:22:07,442][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:22:07,944][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:22:08,447][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:22:08,949][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:22:09,450][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:22:09,952][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:22:10,455][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:22:10,957][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:22:11,460][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:22:11,961][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:22:12,462][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:22:12,964][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:22:13,466][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:22:13,967][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:22:14,469][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:22:14,971][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:22:15,472][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:22:15,973][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:22:16,475][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:22:16,977][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:22:17,478][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:22:17,978][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:22:18,479][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:22:18,980][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:22:19,481][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:22:19,983][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:22:20,484][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:22:20,985][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:22:21,487][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:22:21,988][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:22:22,489][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:22:22,990][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:22:23,492][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:22:23,994][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:22:24,495][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:22:24,995][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:22:25,497][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:22:25,998][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:22:26,500][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:22:27,001][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:22:27,503][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:22:28,005][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:22:28,506][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:22:29,007][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:22:29,509][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:22:30,011][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:22:30,511][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:22:31,012][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:22:31,514][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:22:32,015][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:22:32,516][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:22:33,017][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:22:33,518][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:22:34,018][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:22:34,521][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:22:35,022][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:22:35,523][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:22:36,025][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:22:36,526][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:22:37,027][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:22:37,528][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:22:38,029][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:22:38,531][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:22:39,032][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:22:39,532][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:22:40,033][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:22:40,534][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:22:41,037][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:22:41,541][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:22:42,042][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:22:42,544][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:22:43,046][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:22:43,548][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21757 tokens. [2026-03-26 03:22:44,163][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.24%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-26 03:22:44,909][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:22:44,911][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:22:44,913][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:22:45,595][__main__][INFO] - Iteration 546 took 1m 14s (8.63% Gen, 90.45% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 50h 11m 27s. Estimated total time: 61h 59m 0s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 58s, 500 more iterations: 10h 19m 50s. [2026-03-26 03:22:45,597][__main__][INFO] - Starting iteration 546. [2026-03-26 03:22:45,994][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:22:45,995][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:22:52,926][__main__][INFO] - Number of regex retries in iteration 546: 0 [2026-03-26 03:22:52,927][__main__][INFO] - agents played in iteration 546 are Bob, Alice [2026-03-26 03:22:53,832][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:22:54,416][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:22:54,875][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:22:55,382][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:22:55,885][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:22:56,387][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:22:56,890][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:22:57,392][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:22:57,895][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:22:58,397][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:22:58,899][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:22:59,401][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:22:59,902][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:23:00,404][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:23:00,905][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:23:01,407][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:23:01,909][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:23:02,410][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:23:02,912][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:23:03,414][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:23:03,917][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:23:04,420][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:23:04,922][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:23:05,423][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:23:05,924][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:23:06,426][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:23:06,928][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:23:07,429][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:23:07,931][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:23:08,432][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:23:08,933][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:23:09,434][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:23:09,935][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:23:10,438][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:23:10,940][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:23:11,445][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:23:11,947][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:23:12,449][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:23:12,951][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:23:13,453][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:23:13,955][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:23:14,457][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:23:14,955][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:23:15,452][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:23:15,948][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:23:16,447][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:23:16,945][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:23:17,443][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:23:17,940][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:23:18,439][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:23:18,941][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:23:19,444][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:23:19,946][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:23:20,449][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:23:20,952][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:23:21,453][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:23:21,955][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:23:22,457][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:23:22,963][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:23:23,466][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:23:23,970][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:23:24,472][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:23:24,975][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:23:25,476][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:23:25,980][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:23:26,483][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:23:26,985][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:23:27,487][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:23:27,990][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:23:28,493][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:23:28,996][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:23:29,498][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:23:30,001][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:23:30,503][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:23:31,004][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:23:31,506][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:23:32,007][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:23:32,508][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:23:33,010][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:23:33,510][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:23:34,011][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:23:34,512][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:23:35,014][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:23:35,515][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:23:36,016][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:23:36,518][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:23:37,022][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:23:37,525][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:23:38,027][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:23:38,529][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:23:39,030][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:23:39,532][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:23:40,034][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:23:40,536][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:23:41,040][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:23:41,544][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:23:42,047][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:23:42,549][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:23:43,051][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:23:43,553][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:23:44,055][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:23:44,557][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:23:45,059][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:23:45,561][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:23:46,063][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:23:46,566][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:23:47,067][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:23:47,566][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:23:48,063][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:23:48,562][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:23:49,061][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:23:49,560][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:23:50,058][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:23:50,557][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:23:51,059][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:23:51,562][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:23:52,064][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:23:52,566][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:23:53,069][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:23:53,572][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:23:54,074][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:23:54,576][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:23:55,078][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:23:55,583][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:23:56,086][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:23:56,589][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:23:57,092][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:23:57,594][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:23:58,098][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:23:58,601][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 03:23:59,218][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.30%, Current % of VRAM taken: 60.65%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:04 [2026-03-26 03:23:59,953][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:23:59,955][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:23:59,956][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:24:00,782][__main__][INFO] - Iteration 547 took 1m 14s (9.27% Gen, 89.62% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 50h 30m 38s. Estimated total time: 62h 19m 25s. Time estimates for 10 more iterations: 12m 27s, 100 more iterations: 2h 4m 38s, 500 more iterations: 10h 23m 14s. [2026-03-26 03:24:00,784][__main__][INFO] - Starting iteration 547. [2026-03-26 03:24:01,183][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:24:01,183][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:24:08,402][__main__][INFO] - Number of regex retries in iteration 547: 0 [2026-03-26 03:24:08,403][__main__][INFO] - agents played in iteration 547 are Bob, Alice [2026-03-26 03:24:09,314][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:24:09,888][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:24:10,346][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:24:10,852][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:24:11,356][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:24:11,858][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:24:12,361][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:24:12,863][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:24:13,365][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:24:13,868][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:24:14,370][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:24:14,871][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:24:15,372][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:24:15,874][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:24:16,375][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:24:16,876][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:24:17,378][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:24:17,879][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:24:18,383][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:24:18,885][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:24:19,387][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:24:19,889][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:24:20,390][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:24:20,891][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:24:21,392][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:24:21,894][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:24:22,396][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:24:22,897][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:24:23,398][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:24:23,899][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:24:24,400][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:24:24,900][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:24:25,402][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:24:25,904][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:24:26,406][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:24:26,907][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:24:27,409][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:24:27,910][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:24:28,411][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:24:28,912][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:24:29,414][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:24:29,915][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:24:30,421][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:24:30,926][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:24:31,431][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:24:31,936][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:24:32,440][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:24:32,946][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:24:33,451][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:24:33,957][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:24:34,459][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:24:34,961][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:24:35,462][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:24:35,964][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:24:36,466][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:24:36,968][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:24:37,470][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:24:37,971][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:24:38,473][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:24:38,974][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:24:39,475][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:24:39,976][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:24:40,478][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:24:40,980][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:24:41,483][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:24:41,985][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:24:42,487][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:24:42,989][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:24:43,490][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:24:43,991][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:24:44,492][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:24:44,992][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:24:45,493][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:24:45,994][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:24:46,495][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:24:46,996][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:24:47,498][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:24:47,999][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:24:48,503][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:24:49,004][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:24:49,506][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:24:50,007][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:24:50,509][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:24:51,011][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:24:51,513][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:24:52,016][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:24:52,519][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:24:53,023][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:24:53,526][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:24:54,029][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:24:54,531][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:24:55,032][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:24:55,532][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:24:56,033][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:24:56,535][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:24:57,037][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:24:57,539][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:24:58,042][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:24:58,543][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:24:59,045][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:24:59,547][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:25:00,050][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:25:00,552][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:25:01,053][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:25:01,554][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:25:02,055][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:25:02,560][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:25:03,065][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:25:03,570][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:25:04,075][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:25:04,580][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:25:05,084][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:25:05,589][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:25:06,094][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:25:06,595][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:25:07,100][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:25:07,604][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:25:08,106][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:25:08,608][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:25:09,110][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:25:09,611][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:25:10,113][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:25:10,615][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:25:11,116][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:25:11,621][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:25:12,123][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:25:12,624][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:25:13,126][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:25:13,627][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:25:14,129][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21753 tokens. [2026-03-26 03:25:14,758][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.57%, ΔTime: 00:01:04 [2026-03-26 03:25:15,502][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:25:15,505][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:25:15,506][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:25:16,202][__main__][INFO] - Iteration 548 took 1m 15s (9.62% Gen, 89.45% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 50h 40m 56s. Estimated total time: 62h 30m 59s. Time estimates for 10 more iterations: 12m 30s, 100 more iterations: 2h 5m 1s, 500 more iterations: 10h 25m 9s. [2026-03-26 03:25:16,204][__main__][INFO] - Starting iteration 548. [2026-03-26 03:25:16,604][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:25:16,605][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:25:20,356][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:25:23,974][__main__][INFO] - Number of regex retries in iteration 548: 1 [2026-03-26 03:25:23,975][__main__][INFO] - agents played in iteration 548 are Bob, Alice [2026-03-26 03:25:24,882][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:25:25,468][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:25:25,927][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:25:26,435][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:25:26,940][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:25:27,443][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:25:27,946][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:25:28,449][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:25:28,952][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:25:29,456][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:25:29,958][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:25:30,459][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:25:30,960][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:25:31,461][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:25:31,962][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:25:32,464][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:25:32,964][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:25:33,466][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:25:33,967][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:25:34,468][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:25:34,969][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:25:35,470][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:25:35,970][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:25:36,472][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:25:36,973][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:25:37,474][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:25:37,974][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:25:38,474][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:25:38,975][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:25:39,476][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:25:39,976][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:25:40,476][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:25:40,977][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:25:41,478][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:25:41,979][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:25:42,480][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:25:42,980][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:25:43,481][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:25:43,980][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:25:44,481][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:25:44,982][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:25:45,484][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:25:45,986][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:25:46,488][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:25:46,989][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:25:47,490][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:25:47,990][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:25:48,493][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:25:48,995][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:25:49,496][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:25:49,996][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:25:50,496][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:25:50,996][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:25:51,496][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:25:51,996][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:25:52,496][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:25:52,996][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:25:53,497][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:25:53,997][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:25:54,498][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:25:55,001][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:25:55,503][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:25:56,005][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:25:56,507][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:25:57,009][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:25:57,509][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:25:58,012][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:25:58,515][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:25:59,018][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:25:59,520][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:26:00,024][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:26:00,528][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:26:01,031][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:26:01,535][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:26:02,035][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:26:02,536][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:26:03,036][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:26:03,536][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:26:04,037][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:26:04,538][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:26:05,039][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:26:05,539][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:26:06,042][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:26:06,543][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:26:07,044][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:26:07,545][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:26:08,046][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:26:08,547][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:26:09,048][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:26:09,549][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:26:10,050][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:26:10,549][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:26:11,049][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:26:11,551][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:26:12,052][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:26:12,553][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:26:13,052][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:26:13,552][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:26:14,052][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:26:14,553][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:26:15,053][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:26:15,553][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:26:16,053][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:26:16,553][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:26:17,053][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:26:17,553][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:26:18,055][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:26:18,556][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:26:19,057][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:26:19,557][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:26:20,061][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:26:20,562][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:26:21,064][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:26:21,566][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:26:22,067][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:26:22,568][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:26:23,069][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:26:23,570][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:26:24,072][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:26:24,573][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:26:25,074][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:26:25,574][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:26:26,076][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:26:26,584][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:26:27,087][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:26:27,590][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:26:28,093][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:26:28,598][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:26:29,102][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:26:29,604][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21743 tokens. [2026-03-26 03:26:30,243][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.28%, Current % of VRAM taken: 60.64%, Block Peak % of device VRAM: 62.49%, ΔTime: 00:01:04 [2026-03-26 03:26:30,984][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:26:30,986][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:26:30,987][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:26:31,751][__main__][INFO] - Iteration 549 took 1m 15s (9.81% Gen, 89.17% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 50h 46m 3s. Estimated total time: 62h 37m 22s. Time estimates for 10 more iterations: 12m 31s, 100 more iterations: 2h 5m 14s, 500 more iterations: 10h 26m 13s. [2026-03-26 03:26:31,755][__main__][INFO] - Starting iteration 549. [2026-03-26 03:26:32,153][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:26:32,153][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:26:38,739][__main__][INFO] - Number of regex retries in iteration 549: 0 [2026-03-26 03:26:38,740][__main__][INFO] - agents played in iteration 549 are Bob, Alice [2026-03-26 03:26:39,651][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:26:40,241][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:26:40,699][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:26:41,206][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:26:41,709][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:26:42,210][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:26:42,712][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:26:43,213][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:26:43,713][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:26:44,214][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:26:44,717][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:26:45,219][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:26:45,720][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:26:46,224][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:26:46,725][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:26:47,228][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:26:47,730][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:26:48,231][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:26:48,733][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:26:49,235][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:26:49,739][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:26:50,242][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:26:50,744][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:26:51,246][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:26:51,748][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:26:52,250][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:26:52,751][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:26:53,252][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:26:53,753][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:26:54,255][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:26:54,755][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:26:55,256][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:26:55,757][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:26:56,259][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:26:56,761][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:26:57,263][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:26:57,765][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:26:58,268][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:26:58,771][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:26:59,273][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:26:59,776][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:27:00,278][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:27:00,782][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:27:01,285][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:27:01,788][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:27:02,290][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:27:02,792][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:27:03,295][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:27:03,795][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:27:04,299][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:27:04,819][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:27:05,326][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:27:05,828][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:27:06,330][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:27:06,832][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:27:07,335][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:27:07,837][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:27:08,340][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:27:08,842][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:27:09,345][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:27:09,848][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:27:10,350][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:27:10,853][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:27:11,356][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:27:11,860][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:27:12,363][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:27:12,865][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:27:13,367][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:27:13,868][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:27:14,369][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:27:14,869][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:27:15,370][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:27:15,871][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:27:16,371][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:27:16,873][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:27:17,375][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:27:17,876][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:27:18,379][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:27:18,882][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:27:19,384][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:27:19,885][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:27:20,387][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:27:20,889][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:27:21,390][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:27:21,892][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:27:22,393][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:27:22,895][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:27:23,395][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:27:23,897][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:27:24,399][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:27:24,900][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:27:25,401][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:27:25,902][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:27:26,403][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:27:26,905][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:27:27,407][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:27:27,909][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:27:28,410][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:27:28,912][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:27:29,412][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:27:29,912][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:27:30,413][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:27:30,915][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:27:31,416][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:27:31,917][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:27:32,419][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:27:32,923][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:27:33,425][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:27:33,927][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:27:34,429][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:27:34,931][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:27:35,432][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:27:35,934][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:27:36,436][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:27:36,941][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:27:37,445][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:27:37,949][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:27:38,453][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:27:38,957][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:27:39,461][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:27:39,965][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:27:40,468][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:27:40,971][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:27:41,476][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:27:41,980][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:27:42,482][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:27:42,984][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:27:43,485][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:27:43,987][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:27:44,489][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21745 tokens. [2026-03-26 03:27:45,126][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.27%, Current % of VRAM taken: 60.63%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 03:27:45,871][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:27:45,873][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:27:45,875][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:27:46,609][__main__][INFO] - Iteration 550 took 1m 14s (8.85% Gen, 90.17% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 50h 10m 18s. Estimated total time: 62h 2m 51s. Time estimates for 10 more iterations: 12m 24s, 100 more iterations: 2h 4m 5s, 500 more iterations: 10h 20m 28s. [2026-03-26 03:27:46,611][__main__][INFO] - Starting iteration 550. [2026-03-26 03:27:47,011][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 10 and human policies 1. [2026-03-26 03:27:47,011][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:27:54,015][__main__][INFO] - Number of regex retries in iteration 550: 0 [2026-03-26 03:27:54,016][__main__][INFO] - agents played in iteration 550 are Bob, Alice [2026-03-26 03:27:54,924][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:27:55,507][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:27:55,972][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:27:56,479][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:27:56,988][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:27:57,490][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:27:57,993][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:27:58,496][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:27:58,998][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:27:59,501][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:28:00,006][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:28:00,510][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:28:01,013][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:28:01,517][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:28:02,020][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:28:02,524][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:28:03,029][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:28:03,533][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:28:04,039][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:28:04,551][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:28:05,056][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:28:05,561][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:28:06,067][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:28:06,571][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:28:07,078][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:28:07,586][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:28:08,090][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:28:08,593][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:28:09,096][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:28:09,598][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:28:10,101][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:28:10,604][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:28:11,106][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:28:11,611][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:28:12,113][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:28:12,615][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:28:13,117][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:28:13,620][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:28:14,123][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:28:14,626][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:28:15,129][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:28:15,631][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:28:16,133][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:28:16,636][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:28:17,137][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:28:17,640][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:28:18,143][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:28:18,647][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:28:19,149][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:28:19,651][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:28:20,153][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:28:20,653][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:28:21,153][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:28:21,653][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:28:22,153][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:28:22,655][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:28:23,155][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:28:23,656][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:28:24,156][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:28:24,658][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:28:25,159][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:28:25,661][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:28:26,162][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:28:26,661][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:28:27,162][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:28:27,664][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:28:28,165][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:28:28,666][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:28:29,169][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:28:29,670][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:28:30,171][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:28:30,672][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:28:31,173][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:28:31,675][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:28:32,178][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:28:32,680][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:28:33,183][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:28:33,687][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:28:34,190][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:28:34,694][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:28:35,196][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:28:35,697][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:28:36,199][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:28:36,703][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:28:37,205][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:28:37,708][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:28:38,211][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:28:38,713][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:28:39,216][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:28:39,720][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:28:40,222][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:28:40,723][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:28:41,227][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:28:41,730][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:28:42,231][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:28:42,732][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:28:43,233][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:28:43,734][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:28:44,235][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:28:44,736][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:28:45,238][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:28:45,741][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:28:46,243][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:28:46,744][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:28:47,246][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:28:47,748][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:28:48,250][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:28:48,753][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:28:49,255][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:28:49,756][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:28:50,258][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:28:50,759][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:28:51,262][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:28:51,764][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:28:52,264][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:28:52,765][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:28:53,266][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:28:53,767][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:28:54,267][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:28:54,767][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:28:55,268][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:28:55,768][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:28:56,269][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:28:56,770][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:28:57,270][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:28:57,771][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:28:58,271][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:28:58,772][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:28:59,273][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:28:59,774][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21739 tokens. [2026-03-26 03:29:00,415][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.18%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.41%, ΔTime: 00:01:04 [2026-03-26 03:29:01,154][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:29:01,156][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:29:01,158][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:29:02,572][__main__][INFO] - Iteration 551 took 1m 15s (9.27% Gen, 88.86% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 51h 4m 16s. Estimated total time: 62h 58m 5s. Time estimates for 10 more iterations: 12m 35s, 100 more iterations: 2h 5m 56s, 500 more iterations: 10h 29m 40s. [2026-03-26 03:29:02,574][__main__][INFO] - Starting iteration 551. [2026-03-26 03:29:02,974][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 11 and human policies 1. [2026-03-26 03:29:02,975][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:29:03,600][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:29:05,152][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:29:06,939][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:29:10,018][__main__][INFO] - Number of regex retries in iteration 551: 3 [2026-03-26 03:29:10,018][__main__][INFO] - agents played in iteration 551 are Bob, Alice [2026-03-26 03:29:10,925][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:29:11,516][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:29:11,976][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:29:12,486][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:29:12,990][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:29:13,495][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:29:13,999][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:29:14,503][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:29:15,008][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:29:15,512][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:29:16,012][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:29:16,512][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:29:17,012][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:29:17,512][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:29:18,012][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:29:18,512][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:29:19,012][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:29:19,512][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:29:20,013][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:29:20,517][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:29:21,020][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:29:21,522][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:29:22,024][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:29:22,526][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:29:23,028][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:29:23,530][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:29:24,031][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:29:24,533][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:29:25,034][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:29:25,536][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:29:26,037][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:29:26,542][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:29:27,043][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:29:27,545][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:29:28,047][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:29:28,548][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:29:29,051][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:29:29,552][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:29:30,054][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:29:30,556][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:29:31,057][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:29:31,558][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:29:32,060][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:29:32,563][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:29:33,065][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:29:33,567][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:29:34,069][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:29:34,570][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:29:35,072][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:29:35,573][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:29:36,076][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:29:36,578][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:29:37,083][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:29:37,587][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:29:38,090][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:29:38,591][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:29:39,093][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:29:39,595][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:29:40,095][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:29:40,596][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:29:41,097][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:29:41,601][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:29:42,102][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:29:42,603][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:29:43,104][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:29:43,605][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:29:44,109][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:29:44,613][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:29:45,117][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:29:45,621][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:29:46,126][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:29:46,630][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:29:47,134][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:29:47,638][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:29:48,138][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:29:48,639][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:29:49,141][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:29:49,644][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:29:50,144][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:29:50,645][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:29:51,146][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:29:51,647][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:29:52,149][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:29:52,651][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:29:53,153][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:29:53,655][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:29:54,158][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:29:54,660][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:29:55,162][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:29:55,664][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:29:56,165][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:29:56,667][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:29:57,168][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:29:57,669][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:29:58,170][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:29:58,671][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:29:59,172][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:29:59,674][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:30:00,175][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:30:00,676][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:30:01,177][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:30:01,679][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:30:02,183][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:30:02,684][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:30:03,185][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:30:03,687][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:30:04,188][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:30:04,690][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:30:05,191][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:30:05,693][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:30:06,194][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:30:06,695][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:30:07,197][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:30:07,701][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:30:08,204][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:30:08,705][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:30:09,207][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:30:09,709][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:30:10,210][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:30:10,711][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:30:11,220][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:30:11,724][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:30:12,227][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:30:12,729][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:30:13,230][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:30:13,731][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:30:14,234][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:30:14,740][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:30:15,244][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:30:15,746][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21745 tokens. [2026-03-26 03:30:16,382][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.25%, Current % of VRAM taken: 60.60%, Block Peak % of device VRAM: 62.51%, ΔTime: 00:01:04 [2026-03-26 03:30:17,123][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:30:17,127][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:30:17,129][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:30:17,963][__main__][INFO] - Iteration 552 took 1m 14s (9.39% Gen, 89.49% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 50h 34m 25s. Estimated total time: 62h 29m 30s. Time estimates for 10 more iterations: 12m 29s, 100 more iterations: 2h 4m 59s, 500 more iterations: 10h 24m 55s. [2026-03-26 03:30:17,965][__main__][INFO] - Starting iteration 552. [2026-03-26 03:30:18,362][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 11 and human policies 1. [2026-03-26 03:30:18,363][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:30:25,337][__main__][INFO] - Number of regex retries in iteration 552: 0 [2026-03-26 03:30:25,337][__main__][INFO] - agents played in iteration 552 are Bob, Alice [2026-03-26 03:30:26,246][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:30:26,834][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:30:27,291][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:30:27,799][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:30:28,302][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:30:28,804][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:30:29,307][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:30:29,809][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:30:30,311][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:30:30,813][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:30:31,315][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:30:31,816][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:30:32,317][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:30:32,819][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:30:33,324][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:30:33,826][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:30:34,328][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:30:34,829][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:30:35,332][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:30:35,835][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:30:36,338][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:30:36,841][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:30:37,344][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:30:37,847][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:30:38,350][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:30:38,853][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:30:39,355][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:30:39,858][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:30:40,360][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:30:40,862][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:30:41,366][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:30:41,869][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:30:42,371][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:30:42,873][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:30:43,374][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:30:43,875][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:30:44,376][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:30:44,879][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:30:45,380][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:30:45,882][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:30:46,384][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:30:46,886][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:30:47,389][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:30:47,891][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:30:48,393][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:30:48,895][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:30:49,398][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:30:49,899][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:30:50,402][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:30:50,904][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:30:51,405][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:30:51,905][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:30:52,407][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:30:52,908][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:30:53,409][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:30:53,910][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:30:54,411][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:30:54,912][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:30:55,414][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:30:55,913][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:30:56,416][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:30:56,916][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:30:57,416][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:30:57,916][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:30:58,417][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:30:58,917][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:30:59,419][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:30:59,921][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:31:00,423][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:31:00,925][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:31:01,426][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:31:01,927][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:31:02,429][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:31:02,930][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:31:03,430][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:31:03,931][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:31:04,431][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:31:04,932][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:31:05,432][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:31:05,934][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:31:06,436][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:31:06,940][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:31:07,443][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:31:07,945][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:31:08,447][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:31:08,949][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:31:09,451][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:31:09,953][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:31:10,454][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:31:10,954][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:31:11,457][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:31:11,960][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:31:12,462][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:31:12,964][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:31:13,465][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:31:13,967][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:31:14,468][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:31:14,970][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:31:15,470][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:31:15,971][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:31:16,472][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:31:16,974][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:31:17,474][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:31:17,975][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:31:18,477][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:31:18,980][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:31:19,481][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:31:19,983][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:31:20,485][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:31:20,986][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:31:21,488][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:31:21,990][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:31:22,491][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:31:22,993][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:31:23,494][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:31:23,995][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:31:24,496][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:31:24,998][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:31:25,500][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:31:26,002][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:31:26,503][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:31:27,005][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:31:27,506][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:31:28,007][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:31:28,507][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:31:29,008][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:31:29,509][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:31:30,010][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:31:30,511][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:31:31,012][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21747 tokens. [2026-03-26 03:31:31,633][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.17%, Current % of VRAM taken: 60.53%, Block Peak % of device VRAM: 62.28%, ΔTime: 00:01:04 [2026-03-26 03:31:32,375][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:31:32,377][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:31:32,378][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:31:33,032][__main__][INFO] - Iteration 553 took 1m 14s (9.34% Gen, 89.78% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 50h 17m 11s. Estimated total time: 62h 13m 31s. Time estimates for 10 more iterations: 12m 26s, 100 more iterations: 2h 4m 27s, 500 more iterations: 10h 22m 15s. [2026-03-26 03:31:33,034][__main__][INFO] - Starting iteration 553. [2026-03-26 03:31:33,434][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 11 and human policies 1. [2026-03-26 03:31:33,435][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:31:39,248][mllm.models.large_language_model_local][WARNING] - Response Based on the per-item value information, you have the highest value for balls (10) and Alice values balls the least (1). You should propose to take most of the balls, while distributing hats and books more evenly as the values are similar between you and Alice. Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:31:39,251][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:31:41,123][__main__][INFO] - Number of regex retries in iteration 553: 2 [2026-03-26 03:31:41,397][__main__][INFO] - agents played in iteration 553 are Bob, Alice [2026-03-26 03:31:42,309][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:31:42,891][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:31:43,350][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:31:43,857][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:31:44,360][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:31:44,863][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:31:45,365][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:31:45,868][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:31:46,370][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:31:46,873][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:31:47,378][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:31:47,882][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:31:48,385][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:31:48,888][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:31:49,391][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:31:49,893][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:31:50,396][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:31:50,899][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:31:51,401][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:31:51,904][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:31:52,405][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:31:52,909][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:31:53,411][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:31:53,913][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:31:54,414][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:31:54,916][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:31:55,417][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:31:55,922][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:31:56,425][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:31:56,927][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:31:57,429][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:31:57,930][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:31:58,431][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:31:58,932][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:31:59,433][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:31:59,935][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:32:00,436][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:32:00,937][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:32:01,439][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:32:01,942][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:32:02,443][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:32:02,944][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:32:03,447][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:32:03,949][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:32:04,451][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:32:04,954][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:32:05,456][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:32:05,959][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:32:06,461][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:32:06,963][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:32:07,464][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:32:07,965][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:32:08,466][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:32:08,968][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:32:09,469][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:32:09,970][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:32:10,471][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:32:10,971][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:32:11,474][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:32:11,976][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:32:12,477][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:32:12,978][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:32:13,479][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:32:13,980][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:32:14,482][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:32:14,984][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:32:15,486][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:32:15,989][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:32:16,491][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:32:16,993][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:32:17,495][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:32:17,997][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:32:18,500][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:32:19,003][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:32:19,505][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:32:20,007][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:32:20,509][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:32:21,011][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:32:21,513][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:32:22,015][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:32:22,519][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:32:23,023][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:32:23,524][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:32:24,026][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:32:24,528][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:32:25,030][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:32:25,531][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:32:26,032][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:32:26,534][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:32:27,036][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:32:27,537][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:32:28,038][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:32:28,542][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:32:29,043][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:32:29,544][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:32:30,045][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:32:30,546][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:32:31,047][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:32:31,550][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:32:32,051][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:32:32,552][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:32:33,054][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:32:33,555][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:32:34,055][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:32:34,556][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:32:35,058][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:32:35,561][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:32:36,063][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:32:36,565][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:32:37,071][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:32:37,575][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:32:38,076][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:32:38,579][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:32:39,081][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:32:39,583][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:32:40,085][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:32:40,587][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:32:41,089][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:32:41,593][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:32:42,094][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:32:42,595][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:32:43,096][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:32:43,598][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:32:44,099][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:32:44,602][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:32:45,104][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:32:45,605][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:32:46,107][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:32:46,609][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:32:47,110][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21755 tokens. [2026-03-26 03:32:47,723][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.22%, Current % of VRAM taken: 60.58%, Block Peak % of device VRAM: 62.42%, ΔTime: 00:01:04 [2026-03-26 03:32:48,464][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:32:48,466][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:32:48,468][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:32:53,628][__main__][INFO] - Iteration 554 took 1m 20s (9.93% Gen, 83.64% Train). Generation: 7s, Training: 1m 7s. Estimated remaining time: 54h 52m 1s. Estimated total time: 66h 49m 42s. Time estimates for 10 more iterations: 13m 21s, 100 more iterations: 2h 13m 39s, 500 more iterations: 11h 8m 17s. [2026-03-26 03:32:53,630][__main__][INFO] - Starting iteration 554. [2026-03-26 03:32:54,029][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 11 and human policies 1. [2026-03-26 03:32:54,029][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:32:54,615][mllm.models.large_language_model_local][WARNING] - Response Proposal: 10 hats, 10 books, 10 balls did not match regex: (?i)Proposal:\s*((?:\s*(?P(10|[0-9]))\s*(?Phats?|books?|balls?)\s*,?)+), retry 1/3 [2026-03-26 03:33:00,588][__main__][INFO] - Number of regex retries in iteration 554: 1 [2026-03-26 03:33:00,589][__main__][INFO] - agents played in iteration 554 are Bob, Alice [2026-03-26 03:33:01,493][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:33:02,074][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:33:02,532][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:33:03,041][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:33:03,544][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:33:04,047][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:33:04,549][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:33:05,051][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:33:05,553][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:33:06,055][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:33:06,557][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:33:07,058][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:33:07,559][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:33:08,060][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:33:08,561][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:33:09,061][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:33:09,563][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:33:10,064][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:33:10,566][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:33:11,068][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:33:11,571][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:33:12,072][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:33:12,573][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:33:13,073][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:33:13,575][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:33:14,076][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:33:14,578][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:33:15,079][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:33:15,583][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:33:16,084][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:33:16,585][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:33:17,087][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:33:17,588][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:33:18,090][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:33:18,592][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:33:19,094][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:33:19,596][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:33:20,098][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:33:20,600][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:33:21,102][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:33:21,605][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:33:22,106][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:33:22,608][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:33:23,110][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:33:23,612][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:33:24,112][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:33:24,614][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:33:25,116][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:33:25,618][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:33:26,120][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:33:26,623][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:33:27,125][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:33:27,627][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:33:28,131][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:33:28,632][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:33:29,134][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:33:29,635][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:33:30,137][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:33:30,638][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:33:31,140][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:33:31,641][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:33:32,143][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:33:32,645][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:33:33,146][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:33:33,647][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:33:34,148][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:33:34,650][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:33:35,151][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:33:35,652][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:33:36,153][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:33:36,655][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:33:37,156][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:33:37,658][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:33:38,160][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:33:38,661][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:33:39,162][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:33:39,663][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:33:40,164][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:33:40,665][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:33:41,167][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:33:41,669][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:33:42,170][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:33:42,671][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:33:43,172][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:33:43,673][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:33:44,175][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:33:44,676][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:33:45,175][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:33:45,675][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:33:46,176][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:33:46,677][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:33:47,178][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:33:47,679][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:33:48,181][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:33:48,683][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:33:49,184][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:33:49,685][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:33:50,186][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:33:50,688][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:33:51,189][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:33:51,691][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:33:52,192][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:33:52,693][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:33:53,195][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:33:53,697][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:33:54,198][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:33:54,699][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:33:55,203][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:33:55,705][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:33:56,206][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:33:56,708][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:33:57,210][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:33:57,711][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:33:58,215][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:33:58,717][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128 [2026-03-26 03:33:59,218][mllm.training.trainer_common][INFO] - Processing mini-batch 114 of 128 [2026-03-26 03:33:59,720][mllm.training.trainer_common][INFO] - Processing mini-batch 115 of 128 [2026-03-26 03:34:00,223][mllm.training.trainer_common][INFO] - Processing mini-batch 116 of 128 [2026-03-26 03:34:00,725][mllm.training.trainer_common][INFO] - Processing mini-batch 117 of 128 [2026-03-26 03:34:01,228][mllm.training.trainer_common][INFO] - Processing mini-batch 118 of 128 [2026-03-26 03:34:01,730][mllm.training.trainer_common][INFO] - Processing mini-batch 119 of 128 [2026-03-26 03:34:02,232][mllm.training.trainer_common][INFO] - Processing mini-batch 120 of 128 [2026-03-26 03:34:02,733][mllm.training.trainer_common][INFO] - Processing mini-batch 121 of 128 [2026-03-26 03:34:03,233][mllm.training.trainer_common][INFO] - Processing mini-batch 122 of 128 [2026-03-26 03:34:03,734][mllm.training.trainer_common][INFO] - Processing mini-batch 123 of 128 [2026-03-26 03:34:04,235][mllm.training.trainer_common][INFO] - Processing mini-batch 124 of 128 [2026-03-26 03:34:04,736][mllm.training.trainer_common][INFO] - Processing mini-batch 125 of 128 [2026-03-26 03:34:05,237][mllm.training.trainer_common][INFO] - Processing mini-batch 126 of 128 [2026-03-26 03:34:05,739][mllm.training.trainer_common][INFO] - Processing mini-batch 127 of 128 [2026-03-26 03:34:06,240][mllm.training.trainer_common][INFO] - Accumulated the policy gradient loss for 21737 tokens. [2026-03-26 03:34:06,990][mllm.training.trainer_common][INFO] - For task: Apply reinforce step, ΔVRAM % (total): 14.21%, Current % of VRAM taken: 60.57%, Block Peak % of device VRAM: 62.32%, ΔTime: 00:01:04 [2026-03-26 03:34:07,733][mllm.training.trainer_common][INFO] - Saved main optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/policy_optimizer_state.pt [2026-03-26 03:34:07,735][mllm.training.trainer_common][INFO] - Saved critic optimizer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/critic_optimizer_state.pt [2026-03-26 03:34:07,737][mllm.training.trainer_common][INFO] - Saved trainer state to /scratch/muqeeth/llm_negotiation/2026_03/split_no_comm_naive_seed1337/seed_1337/agent_trainer/trainer_annealing_state.pkl [2026-03-26 03:34:08,368][__main__][INFO] - Iteration 555 took 1m 14s (8.82% Gen, 90.33% Train). Generation: 6s, Training: 1m 7s. Estimated remaining time: 49h 58m 4s. Estimated total time: 61h 56m 59s. Time estimates for 10 more iterations: 12m 23s, 100 more iterations: 2h 3m 53s, 500 more iterations: 10h 19m 29s. [2026-03-26 03:34:08,370][__main__][INFO] - Starting iteration 555. [2026-03-26 03:34:08,769][__main__][INFO] - Inference policies count is regular policies 2 and buffer policies 11 and human policies 1. [2026-03-26 03:34:08,770][__main__][INFO] - Hard coded buffer agents are set to False with prob 0 [2026-03-26 03:34:15,528][__main__][INFO] - Number of regex retries in iteration 555: 0 [2026-03-26 03:34:15,529][__main__][INFO] - agents played in iteration 555 are Bob, Alice [2026-03-26 03:34:16,435][mllm.training.trainer_independent][INFO] - Sharing advantage data. [2026-03-26 03:34:17,273][mllm.training.trainer_common][INFO] - Processing mini-batch 0 of 128 [2026-03-26 03:34:17,729][mllm.training.trainer_common][INFO] - Processing mini-batch 1 of 128 [2026-03-26 03:34:18,235][mllm.training.trainer_common][INFO] - Processing mini-batch 2 of 128 [2026-03-26 03:34:18,737][mllm.training.trainer_common][INFO] - Processing mini-batch 3 of 128 [2026-03-26 03:34:19,240][mllm.training.trainer_common][INFO] - Processing mini-batch 4 of 128 [2026-03-26 03:34:19,743][mllm.training.trainer_common][INFO] - Processing mini-batch 5 of 128 [2026-03-26 03:34:20,245][mllm.training.trainer_common][INFO] - Processing mini-batch 6 of 128 [2026-03-26 03:34:20,747][mllm.training.trainer_common][INFO] - Processing mini-batch 7 of 128 [2026-03-26 03:34:21,249][mllm.training.trainer_common][INFO] - Processing mini-batch 8 of 128 [2026-03-26 03:34:21,751][mllm.training.trainer_common][INFO] - Processing mini-batch 9 of 128 [2026-03-26 03:34:22,253][mllm.training.trainer_common][INFO] - Processing mini-batch 10 of 128 [2026-03-26 03:34:22,754][mllm.training.trainer_common][INFO] - Processing mini-batch 11 of 128 [2026-03-26 03:34:23,254][mllm.training.trainer_common][INFO] - Processing mini-batch 12 of 128 [2026-03-26 03:34:23,755][mllm.training.trainer_common][INFO] - Processing mini-batch 13 of 128 [2026-03-26 03:34:24,256][mllm.training.trainer_common][INFO] - Processing mini-batch 14 of 128 [2026-03-26 03:34:24,756][mllm.training.trainer_common][INFO] - Processing mini-batch 15 of 128 [2026-03-26 03:34:25,257][mllm.training.trainer_common][INFO] - Processing mini-batch 16 of 128 [2026-03-26 03:34:25,758][mllm.training.trainer_common][INFO] - Processing mini-batch 17 of 128 [2026-03-26 03:34:26,259][mllm.training.trainer_common][INFO] - Processing mini-batch 18 of 128 [2026-03-26 03:34:26,759][mllm.training.trainer_common][INFO] - Processing mini-batch 19 of 128 [2026-03-26 03:34:27,261][mllm.training.trainer_common][INFO] - Processing mini-batch 20 of 128 [2026-03-26 03:34:27,762][mllm.training.trainer_common][INFO] - Processing mini-batch 21 of 128 [2026-03-26 03:34:28,264][mllm.training.trainer_common][INFO] - Processing mini-batch 22 of 128 [2026-03-26 03:34:28,764][mllm.training.trainer_common][INFO] - Processing mini-batch 23 of 128 [2026-03-26 03:34:29,265][mllm.training.trainer_common][INFO] - Processing mini-batch 24 of 128 [2026-03-26 03:34:29,766][mllm.training.trainer_common][INFO] - Processing mini-batch 25 of 128 [2026-03-26 03:34:30,268][mllm.training.trainer_common][INFO] - Processing mini-batch 26 of 128 [2026-03-26 03:34:30,770][mllm.training.trainer_common][INFO] - Processing mini-batch 27 of 128 [2026-03-26 03:34:31,271][mllm.training.trainer_common][INFO] - Processing mini-batch 28 of 128 [2026-03-26 03:34:31,772][mllm.training.trainer_common][INFO] - Processing mini-batch 29 of 128 [2026-03-26 03:34:32,273][mllm.training.trainer_common][INFO] - Processing mini-batch 30 of 128 [2026-03-26 03:34:32,774][mllm.training.trainer_common][INFO] - Processing mini-batch 31 of 128 [2026-03-26 03:34:33,275][mllm.training.trainer_common][INFO] - Processing mini-batch 32 of 128 [2026-03-26 03:34:33,775][mllm.training.trainer_common][INFO] - Processing mini-batch 33 of 128 [2026-03-26 03:34:34,276][mllm.training.trainer_common][INFO] - Processing mini-batch 34 of 128 [2026-03-26 03:34:34,776][mllm.training.trainer_common][INFO] - Processing mini-batch 35 of 128 [2026-03-26 03:34:35,277][mllm.training.trainer_common][INFO] - Processing mini-batch 36 of 128 [2026-03-26 03:34:35,778][mllm.training.trainer_common][INFO] - Processing mini-batch 37 of 128 [2026-03-26 03:34:36,278][mllm.training.trainer_common][INFO] - Processing mini-batch 38 of 128 [2026-03-26 03:34:36,780][mllm.training.trainer_common][INFO] - Processing mini-batch 39 of 128 [2026-03-26 03:34:37,281][mllm.training.trainer_common][INFO] - Processing mini-batch 40 of 128 [2026-03-26 03:34:37,782][mllm.training.trainer_common][INFO] - Processing mini-batch 41 of 128 [2026-03-26 03:34:38,283][mllm.training.trainer_common][INFO] - Processing mini-batch 42 of 128 [2026-03-26 03:34:38,783][mllm.training.trainer_common][INFO] - Processing mini-batch 43 of 128 [2026-03-26 03:34:39,284][mllm.training.trainer_common][INFO] - Processing mini-batch 44 of 128 [2026-03-26 03:34:39,784][mllm.training.trainer_common][INFO] - Processing mini-batch 45 of 128 [2026-03-26 03:34:40,285][mllm.training.trainer_common][INFO] - Processing mini-batch 46 of 128 [2026-03-26 03:34:40,785][mllm.training.trainer_common][INFO] - Processing mini-batch 47 of 128 [2026-03-26 03:34:41,288][mllm.training.trainer_common][INFO] - Processing mini-batch 48 of 128 [2026-03-26 03:34:41,790][mllm.training.trainer_common][INFO] - Processing mini-batch 49 of 128 [2026-03-26 03:34:42,289][mllm.training.trainer_common][INFO] - Processing mini-batch 50 of 128 [2026-03-26 03:34:42,789][mllm.training.trainer_common][INFO] - Processing mini-batch 51 of 128 [2026-03-26 03:34:43,290][mllm.training.trainer_common][INFO] - Processing mini-batch 52 of 128 [2026-03-26 03:34:43,790][mllm.training.trainer_common][INFO] - Processing mini-batch 53 of 128 [2026-03-26 03:34:44,290][mllm.training.trainer_common][INFO] - Processing mini-batch 54 of 128 [2026-03-26 03:34:44,791][mllm.training.trainer_common][INFO] - Processing mini-batch 55 of 128 [2026-03-26 03:34:45,292][mllm.training.trainer_common][INFO] - Processing mini-batch 56 of 128 [2026-03-26 03:34:45,791][mllm.training.trainer_common][INFO] - Processing mini-batch 57 of 128 [2026-03-26 03:34:46,291][mllm.training.trainer_common][INFO] - Processing mini-batch 58 of 128 [2026-03-26 03:34:46,792][mllm.training.trainer_common][INFO] - Processing mini-batch 59 of 128 [2026-03-26 03:34:47,292][mllm.training.trainer_common][INFO] - Processing mini-batch 60 of 128 [2026-03-26 03:34:47,791][mllm.training.trainer_common][INFO] - Processing mini-batch 61 of 128 [2026-03-26 03:34:48,292][mllm.training.trainer_common][INFO] - Processing mini-batch 62 of 128 [2026-03-26 03:34:48,793][mllm.training.trainer_common][INFO] - Processing mini-batch 63 of 128 [2026-03-26 03:34:49,292][mllm.training.trainer_common][INFO] - Processing mini-batch 64 of 128 [2026-03-26 03:34:49,793][mllm.training.trainer_common][INFO] - Processing mini-batch 65 of 128 [2026-03-26 03:34:50,293][mllm.training.trainer_common][INFO] - Processing mini-batch 66 of 128 [2026-03-26 03:34:50,793][mllm.training.trainer_common][INFO] - Processing mini-batch 67 of 128 [2026-03-26 03:34:51,293][mllm.training.trainer_common][INFO] - Processing mini-batch 68 of 128 [2026-03-26 03:34:51,793][mllm.training.trainer_common][INFO] - Processing mini-batch 69 of 128 [2026-03-26 03:34:52,295][mllm.training.trainer_common][INFO] - Processing mini-batch 70 of 128 [2026-03-26 03:34:52,794][mllm.training.trainer_common][INFO] - Processing mini-batch 71 of 128 [2026-03-26 03:34:53,294][mllm.training.trainer_common][INFO] - Processing mini-batch 72 of 128 [2026-03-26 03:34:53,794][mllm.training.trainer_common][INFO] - Processing mini-batch 73 of 128 [2026-03-26 03:34:54,295][mllm.training.trainer_common][INFO] - Processing mini-batch 74 of 128 [2026-03-26 03:34:54,795][mllm.training.trainer_common][INFO] - Processing mini-batch 75 of 128 [2026-03-26 03:34:55,296][mllm.training.trainer_common][INFO] - Processing mini-batch 76 of 128 [2026-03-26 03:34:55,796][mllm.training.trainer_common][INFO] - Processing mini-batch 77 of 128 [2026-03-26 03:34:56,296][mllm.training.trainer_common][INFO] - Processing mini-batch 78 of 128 [2026-03-26 03:34:56,797][mllm.training.trainer_common][INFO] - Processing mini-batch 79 of 128 [2026-03-26 03:34:57,299][mllm.training.trainer_common][INFO] - Processing mini-batch 80 of 128 [2026-03-26 03:34:57,800][mllm.training.trainer_common][INFO] - Processing mini-batch 81 of 128 [2026-03-26 03:34:58,301][mllm.training.trainer_common][INFO] - Processing mini-batch 82 of 128 [2026-03-26 03:34:58,802][mllm.training.trainer_common][INFO] - Processing mini-batch 83 of 128 [2026-03-26 03:34:59,302][mllm.training.trainer_common][INFO] - Processing mini-batch 84 of 128 [2026-03-26 03:34:59,804][mllm.training.trainer_common][INFO] - Processing mini-batch 85 of 128 [2026-03-26 03:35:00,306][mllm.training.trainer_common][INFO] - Processing mini-batch 86 of 128 [2026-03-26 03:35:00,807][mllm.training.trainer_common][INFO] - Processing mini-batch 87 of 128 [2026-03-26 03:35:01,307][mllm.training.trainer_common][INFO] - Processing mini-batch 88 of 128 [2026-03-26 03:35:01,808][mllm.training.trainer_common][INFO] - Processing mini-batch 89 of 128 [2026-03-26 03:35:02,309][mllm.training.trainer_common][INFO] - Processing mini-batch 90 of 128 [2026-03-26 03:35:02,809][mllm.training.trainer_common][INFO] - Processing mini-batch 91 of 128 [2026-03-26 03:35:03,310][mllm.training.trainer_common][INFO] - Processing mini-batch 92 of 128 [2026-03-26 03:35:03,811][mllm.training.trainer_common][INFO] - Processing mini-batch 93 of 128 [2026-03-26 03:35:04,313][mllm.training.trainer_common][INFO] - Processing mini-batch 94 of 128 [2026-03-26 03:35:04,814][mllm.training.trainer_common][INFO] - Processing mini-batch 95 of 128 [2026-03-26 03:35:05,315][mllm.training.trainer_common][INFO] - Processing mini-batch 96 of 128 [2026-03-26 03:35:05,815][mllm.training.trainer_common][INFO] - Processing mini-batch 97 of 128 [2026-03-26 03:35:06,314][mllm.training.trainer_common][INFO] - Processing mini-batch 98 of 128 [2026-03-26 03:35:06,815][mllm.training.trainer_common][INFO] - Processing mini-batch 99 of 128 [2026-03-26 03:35:07,316][mllm.training.trainer_common][INFO] - Processing mini-batch 100 of 128 [2026-03-26 03:35:07,817][mllm.training.trainer_common][INFO] - Processing mini-batch 101 of 128 [2026-03-26 03:35:08,317][mllm.training.trainer_common][INFO] - Processing mini-batch 102 of 128 [2026-03-26 03:35:08,819][mllm.training.trainer_common][INFO] - Processing mini-batch 103 of 128 [2026-03-26 03:35:09,320][mllm.training.trainer_common][INFO] - Processing mini-batch 104 of 128 [2026-03-26 03:35:09,822][mllm.training.trainer_common][INFO] - Processing mini-batch 105 of 128 [2026-03-26 03:35:10,323][mllm.training.trainer_common][INFO] - Processing mini-batch 106 of 128 [2026-03-26 03:35:10,824][mllm.training.trainer_common][INFO] - Processing mini-batch 107 of 128 [2026-03-26 03:35:11,327][mllm.training.trainer_common][INFO] - Processing mini-batch 108 of 128 [2026-03-26 03:35:11,828][mllm.training.trainer_common][INFO] - Processing mini-batch 109 of 128 [2026-03-26 03:35:12,329][mllm.training.trainer_common][INFO] - Processing mini-batch 110 of 128 [2026-03-26 03:35:12,829][mllm.training.trainer_common][INFO] - Processing mini-batch 111 of 128 [2026-03-26 03:35:13,329][mllm.training.trainer_common][INFO] - Processing mini-batch 112 of 128 [2026-03-26 03:35:13,830][mllm.training.trainer_common][INFO] - Processing mini-batch 113 of 128